Datasets:
id stringlengths 15 15 | conversations listlengths 3 3 | language stringclasses 1
value | extra stringlengths 59 572 |
|---|---|---|---|
-0Gj8-vB1q4.wav | [
{
"from": "User",
"value": "What can you say about this music recording?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-0Gj8-vB1q4.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['low quality', 'sustained strings melody', 'soft female vocal', 'mellow piano melody', 'sad', 'soulful', 'ballad']"}} |
-0vPFx-wRRI.wav | [
{
"from": "User",
"value": "Describe this music in a few sentences.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-0vPFx-wRRI.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['amateur recording', 'finger snipping', 'male mid range voice singing', 'reverb']"}} |
-0xzrMun0Rs.wav | [
{
"from": "User",
"value": "Summarize the music : genre, strings, mood, where can it be played, quality etc...",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-0xzrMun0Rs.wav",
"type": "audio",
"duration": 10,
"offse... | en | {"custom_metadata": {"aspect_list": "['backing track', 'jazzy', 'digital drums', 'piano', 'e-bass', 'trumpet', 'acoustic guitar', 'digital keyboard song', 'medium tempo']"}} |
-1OlgJWehn8.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-1OlgJWehn8.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['instrumental', 'white noise', 'female vocalisation', 'three unrelated tracks', 'electric guitar harmony', 'bass guitar', 'keyboard harmony', 'female lead vocalisation', 'keyboard harmony', 'slick drumming', 'boomy bass drops', 'male voice backup vocalisation']"}} |
-1UWSisR2zo.wav | [
{
"from": "User",
"value": "Write down a complete breakdown of the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-1UWSisR2zo.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['live performance', 'poor audio quality', 'ambient noises', 'school dance program', 'crowd noise', 'high gain volume', 'hissing tones', 'medium tempo', 'techno dance song', 'male singer', 'groovy bass line', 'techno dance rhythm', 'keyboard accompaniment', 'kids dancing', 'noisy cr... |
-3Kv4fdm7Uk.wav | [
{
"from": "User",
"value": "What can you say about this music recording?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-3Kv4fdm7Uk.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Ass... | en | {"custom_metadata": {"aspect_list": "['steeldrum', 'higher register', 'amateur recording']"}} |
-4SYC2YgzL8.wav | [
{
"from": "User",
"value": "How would you describe this musical excerpt?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-4SYC2YgzL8.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Ass... | en | {"custom_metadata": {"aspect_list": "['solo live direct input acoustic guitar strumming', 'airy suspended open chords', 'low fidelity', 'ambient sounds', 'paper shuffling']"}} |
-5FoeegAgvU.wav | [
{
"from": "User",
"value": "Describe this music in a few sentences.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-5FoeegAgvU.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['brass', 'double bass', 'strings', 'instrumental', 'no voice', 'percussion']"}} |
-6HBGg1cAI0.wav | [
{
"from": "User",
"value": "Please describe the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-6HBGg1cAI0.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"value": "... | en | {"custom_metadata": {"aspect_list": "['folk song', 'traditional song', 'middle eastern song', 'male voice', 'darbuka', 'oud instrument', 'moderate tempo', 'middle eastern instruments']"}} |
-7B9tPuIP-w.wav | [
{
"from": "User",
"value": "Describe this music in a few sentences.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-7B9tPuIP-w.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['male vocalist', 'medium fast tempo', 'monologue', 'background music', 'hit songs', 'retro', 'narrator', 'narration', 'documentary', 'animated singing', 'enthusiastic drumming', 'cymbal ride', 'electric guitar', 'groovy bass lines', 'rock and rock', 'classic rock and rock', 'muffle... |
-88me9bBzrk.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-88me9bBzrk.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['hindi', 'tablas', 'shrutibox', 'bansuri flute', 'medium tempo']"}} |
-8C-gydUbR8.wav | [
{
"from": "User",
"value": "Give me a report on the music played",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-8C-gydUbR8.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['gospel music', 'poor sound quality', 'children choir', 'medium tempo', 'black gospel music', 'distorted sound quality', 'meditative', 'devotional', 'inspiring', 'motivational', 'christian contemporary music', 'steady drumming rhythm', 'groovy bass line', 'keyboard harmony', 'retro... |
-8cgbhIR_pw.wav | [
{
"from": "User",
"value": "Describe this music in a few sentences.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-8cgbhIR_pw.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['low quality', 'passionate muddy male vocal', 'arpeggiated acoustic guitar melody', 'noisy', 'muddy', 'cover', 'emotional', 'ballad', 'raw', 'messy']"}} |
-BHPu-dPmWQ.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-BHPu-dPmWQ.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"v... | en | {"custom_metadata": {"aspect_list": "['intimate wide mixed vocals', 'synth lead melody', 'punchy kick', 'noisy snare', 'claps', 'groovy bass guitar', 'tinny wide hi hats', 'short snare roll', 'alternative/indie', 'electric guitar melody', 'easygoing', 'melancholic']"}} |
-Bu7YaslRW0.wav | [
{
"from": "User",
"value": "What can you say about this music recording?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-Bu7YaslRW0.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Ass... | en | {"custom_metadata": {"aspect_list": "['atmospheric', 'cinematic', 'calming', 'flute/string/brass sound', 'cymbals', 'synth pad drone', 'slow tempo']"}} |
-ByoSbgzr4M.wav | [
{
"from": "User",
"value": "Give me a report on the music played",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-ByoSbgzr4M.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Assistant",... | en | {"custom_metadata": {"aspect_list": "['instrumental', 'electric guitar', 'stringed instrument', 'vibrato', 'sonic power', 'amplified guitar', 'fast tempo', 'rapid', 'vigorous', 'dexterous', 'skilled', 'practice', 'intense', 'rock', 'hard rock', 'home recording']"}} |
-EVRXQpt1-8.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-EVRXQpt1-8.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"v... | en | {"custom_metadata": {"aspect_list": "['oriental/ballad', 'guitar like instrumental', 'bass', 'male voice singing', 'female backing voice singing', 'sad', 'slow tempo', 'harp']"}} |
-Gf4Ihv1zwc.wav | [
{
"from": "User",
"value": "What are the characteristics of this music?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-Gf4Ihv1zwc.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistan... | en | {"custom_metadata": {"aspect_list": "['christmas', 'festive', 'celtic', 'female vocal', 'melodic singing', 'strings', 'piano', 'harp', 'dulcimer', 'calming', 'positive']"}} |
-IZbvEO9wzU.wav | [
{
"from": "User",
"value": "Write down a complete breakdown of the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-IZbvEO9wzU.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Ass... | en | {"custom_metadata": {"aspect_list": "['jingle', 'chipmunk vocal', 'transposed instruments', 'piano', 'electronic drums', 'high pitch', 'irritating', 'poor quality', 'bizarre']"}} |
-JvB5AL59fM.wav | [
{
"from": "User",
"value": "Describe this music in a few sentences.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-JvB5AL59fM.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['rock', 'e-guitars', 'e-bass', 'acoustic drums', 'keys', 'female voice singing', 'male backing voice', 'uptempo']"}} |
-M6K3QoHh40.wav | [
{
"from": "User",
"value": "Write down a complete breakdown of the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-M6K3QoHh40.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Ass... | en | {"custom_metadata": {"aspect_list": "['low quality', 'r&b', 'boomy', 'passionate male vocal', 'claps', 'shimmering hi hats', 'groovy bass', 'noisy', 'passionate', 'speaker', 'reverberant', '4 on the floor kick']"}} |
-OAyRsvFGgc.wav | [
{
"from": "User",
"value": "What can you say about this music recording?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-OAyRsvFGgc.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['low quality', 'noisy', 'cover', 'rock', 'electric guitar solo melody', 'playback instrumental', 'punchy snare', 'punchy kick', 'smooth bass', 'soft cymbals', 'passionate', 'muffled']"}} |
-OUIEnuNd1I.wav | [
{
"from": "User",
"value": "Summarize the music : genre, strings, mood, where can it be played, quality etc...",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-OUIEnuNd1I.wav",
"type": "audio",
"duration": 10.008,
"o... | en | {"custom_metadata": {"aspect_list": "['classical', 'baroque', 'canon', 'single instrument', 'instrumental', 'harp', 'catchy', 'iconic', 'calming', 'hopeful', 'positive', 'wedding music']"}} |
-Q9MTRXS4bE.wav | [
{
"from": "User",
"value": "Analyze the music and describe what you hear",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-Q9MTRXS4bE.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Ass... | en | {"custom_metadata": {"aspect_list": "['instrumental', 'fast tempo', 'happy', 'perky', 'punchy', 'background sounds super imposed by music', 'digital pads', 'lively', 'synthesised violins', 'upbeat', 'synthesiser arrangements', 'lively piano harmony', 'punchy digital drum rhythm', 'sound of beeping', 'funky bass line', ... |
-QuWdnmn-kM.wav | [
{
"from": "User",
"value": "Write a detailed description of the music, including the recording quality, musical instruments, and any other specific features.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-QuWdnmn-kM.wav",
... | en | {"custom_metadata": {"aspect_list": "['sustained piano synth', 'lullaby', 'bright xylophone', 'mellow mellody', 'bass guitar', 'dreamy', 'kids music', 'slow tempo', 'nostalgic', 'cello', 'no vocals', 'sleepy']"}} |
-RYtUAsNhF0.wav | [
{
"from": "User",
"value": "Summarize the music : genre, strings, mood, where can it be played, quality etc...",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-RYtUAsNhF0.wav",
"type": "audio",
"duration": 10.008,
"o... | en | {"custom_metadata": {"aspect_list": "['poor quality', 'no singer', 'instrumental', 'piano', 'strings', 'acoustic guitar', 'gentle', 'mellow', 'optimistic']"}} |
-SD43H5B5hE.wav | [
{
"from": "User",
"value": "Analyze the music and describe what you hear",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-SD43H5B5hE.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['soundeffects', 'cinematic', 'amateur recording']"}} |
-SWaCArvQug.wav | [
{
"from": "User",
"value": "Analyze the music and describe what you hear",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-SWaCArvQug.wav",
"type": "audio",
"duration": 9.914,
"offset": null
},
{
"from": "Assi... | en | {"custom_metadata": {"aspect_list": "['ambient room noise', 'instrumental', 'male singer', 'beep tones', 'wind noise', 'doorsteps', 'noise', 'non musical tones', 'home improvement video', 'unimpressive sounds', 'drawer closing', 'home video', 'passionate singing', 'medium tempo']"}} |
-U16iKiXGuY.wav | [
{
"from": "User",
"value": "How would you describe this musical excerpt?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-U16iKiXGuY.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['low quality', 'mellow piano melody', 'noisy', 'lip smack noise', 'r&b', 'emotional female vocal', 'live performance']"}} |
-Umconw-CRE.wav | [
{
"from": "User",
"value": "What are the characteristics of this music?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-Umconw-CRE.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Assi... | en | {"custom_metadata": {"aspect_list": "['low quality', 'noisy', 'muffled', 'electric guitar solo melody', 'cover', 'rock instrumental playback', 'passionate', 'emotional']"}} |
-Vo4CAMX26U.wav | [
{
"from": "User",
"value": "Write down a complete breakdown of the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-Vo4CAMX26U.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['low quality', 'low windpipe vocal sounds', 'nature atmosphere sound effect', 'birds chirping', 'water flowing sound effect', 'harsh', 'loud']"}} |
-WvVG0wHcTc.wav | [
{
"from": "User",
"value": "Write down a complete breakdown of the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-WvVG0wHcTc.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['classical', 'sustained violin melody', 'crowd clapping', 'shimmering hi hats', 'theremin solo', 'subtle female vocal', 'live performance', 'electric guitar melody', 'low quality', 'noisy', 'mono', 'passionate', 'emotional']"}} |
-YIT4HBM__g.wav | [
{
"from": "User",
"value": "Give me a report on the music played",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-YIT4HBM__g.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Assistant",... | en | {"custom_metadata": {"aspect_list": "['female singer', 'high notes', 'choral harmony', 'ethereal', 'vocal vibrations', 'ethereal', 'soprano', 'alto', 'whirring sound', 'seconds', 'melodic', 'angelic', 'celestial', 'no instruments', 'sound of chatter', 'rustling', 'scuffling', 'harmonious', 'amateur recording', 'mediocr... |
-bgHkxwoliw.wav | [
{
"from": "User",
"value": "Write a detailed description of the music, including the recording quality, musical instruments, and any other specific features.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-bgHkxwoliw.wav",
... | en | {"custom_metadata": {"aspect_list": "['pop', 'digital drums', 'e-guitar', 'keyboard melodies', 'male voice singing', 'higher register', 'bass', 'uptempo', 'positive atmosphere']"}} |
-dVgUSrR8g4.wav | [
{
"from": "User",
"value": "Please describe the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-dVgUSrR8g4.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"value": "... | en | {"custom_metadata": {"aspect_list": "['intense', 'vigorous', 'loud electric guitar feedback', 'intense', 'psychedelic', 'trap', 'trance', 'hard rock', 'enthusiastic', 'energetic', 'spirited', 'hyper', 'fast tempo', 'goth rock', 'heavy metal', 'amplified guitar', 'intense drumming', 'chattering sounds', 'scratching', '... |
-e4wXAy1iVo.wav | [
{
"from": "User",
"value": "What are the characteristics of this music?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-e4wXAy1iVo.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistan... | en | {"custom_metadata": {"aspect_list": "['pop', 'ukulele', 'female voices singing', 'harmony', 'amateur recording', 'medium to uptempo']"}} |
-eDAoheZrY8.wav | [
{
"from": "User",
"value": "How would you describe this musical excerpt?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-eDAoheZrY8.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['movie soundtrack', 'philharmonic orchestra', 'crescendo', 'booming lower harmony', 'average audio quality', 'tense', 'sci-fi music', 'string section harmony', 'suspenseful music', 'horn section', 'drums playing slowly', 'instrumental music', 'mysterious', 'science fiction', 'explo... |
-f1DNyngKVY.wav | [
{
"from": "User",
"value": "What are the characteristics of this music?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-f1DNyngKVY.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistan... | en | {"custom_metadata": {"aspect_list": "['sitar', 'no singer', 'instrumental', 'single instrument', 'medium-to-high range', 'transcendental', 'relaxing', 'calming', 'meditation']"}} |
-f6s6kQEHFY.wav | [
{
"from": "User",
"value": "How would you describe this musical excerpt?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-f6s6kQEHFY.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Ass... | en | {"custom_metadata": {"aspect_list": "['slow pop', 'ethereal song', 'ambient sounds', 'no lyrics', 'female voice', 'autotune voice', 'piano song', 'synth sounds', 'slow tempo', 'bass', 'no percussion', 'haunting melody']"}} |
-hSMzrWZCAE.wav | [
{
"from": "User",
"value": "What are the characteristics of this music?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-hSMzrWZCAE.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistan... | en | {"custom_metadata": {"aspect_list": "['male voice', 'electric guitar', 'distortion effect', 'drums', 'synth bass', 'pop rock genre']"}} |
-hYRFCQdbLg.wav | [
{
"from": "User",
"value": "What can you say about this music recording?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-hYRFCQdbLg.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Ass... | en | {"custom_metadata": {"aspect_list": "['upbeat instrumental', 'loud marimba melody', 'noisy', 'low quality']"}} |
-i9gpG3vPwA.wav | [
{
"from": "User",
"value": "Describe this music in a few sentences.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-i9gpG3vPwA.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Assistan... | en | {"custom_metadata": {"aspect_list": "['instrumental', 'two tracks', 'electronic music', 'harmonic', 'futuristic', 'engaging', 'captivating', 'dance groove', 'electro pop', 'unrelated tracks', 'synthesiser articulation', 'funky drumming', 'enthusiastic digital drum rhythm', 'keyboard harmony', 'dance pop', 'edm', 'pleas... |
-i9uQMysy_A.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-i9uQMysy_A.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"v... | en | {"custom_metadata": {"aspect_list": "['beat boxing', 'vocal percussion', 'mimicking drum machines', 'vocal percussion simulation', 'vocal sound effects', 'rap', 'hip hop', 'vocalisation', 'rapid', 'vigorous drumming sound', 'digital drum sounds', 'vocal percussion', 'vocal turn table', 'vigorous', 'tireless', 'energeti... |
-kpR93atgd8.wav | [
{
"from": "User",
"value": "Summarize the music : genre, strings, mood, where can it be played, quality etc...",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-kpR93atgd8.wav",
"type": "audio",
"duration": 10,
"offse... | en | {"custom_metadata": {"aspect_list": "['ska', 'saxophone', 'e-guitar', 'acoustic drums', 'percussion', 'keys', 'e-bass', 'fast tempo', 'uplifting energy']"}} |
-lPXTBXa0tE.wav | [
{
"from": "User",
"value": "Describe this music in a few sentences.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-lPXTBXa0tE.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Assistan... | en | {"custom_metadata": {"aspect_list": "['bad audio quality', 'vintage guitar tone', 'passionate', 'spirited', 'guitar demo', 'soloist', 'antique guitar', 'youtube music class', 'master class', 'buzzing noise', 'instrumental music', 'ambient room noise', 'bad audio quality', 'super tone unique tone', 'melancholic', 'count... |
-m9pH0WXQto.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-m9pH0WXQto.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"v... | en | {"custom_metadata": {"aspect_list": "['electro pop', 'low quality', 'flat female vocal', 'wide background female doubling vocals', 'airplane sound effect', 'explosion sound effect', 'arpeggiated synth melody', 'shimmering tinny bells melody', 'energetic muffled crash cymbals', 'quiet drums', 'boomy groovy bass', 'simpl... |
-nlkWWphiaM.wav | [
{
"from": "User",
"value": "Analyze the music and describe what you hear",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-nlkWWphiaM.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['low quality', 'live performance', 'fruity male vocal', 'accordion melody', 'acoustic rhythm guitar', 'shimmering bells', 'emotional', 'hopeful', 'mono', 'noisy']"}} |
-pUfYFcsgG4.wav | [
{
"from": "User",
"value": "Summarize the music : genre, strings, mood, where can it be played, quality etc...",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-pUfYFcsgG4.wav",
"type": "audio",
"duration": 10,
"offse... | en | {"custom_metadata": {"aspect_list": "['amateur recording', 'bell sounds', 'birds singing']"}} |
-qcTD2o6I9s.wav | [
{
"from": "User",
"value": "What are the characteristics of this music?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-qcTD2o6I9s.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Assi... | en | {"custom_metadata": {"aspect_list": "['techno/pop', 'digital drums', 'synth lead', 'organ', 'pad sounds', 'male voice singing/rapping', 'backing vocals', 'fast tempo']"}} |
-r2-9oyIzkQ.wav | [
{
"from": "User",
"value": "Please describe the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-r2-9oyIzkQ.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"value": "... | en | {"custom_metadata": {"aspect_list": "['romance', 'wide background crowd screaming', 'electric guitar lick', 'emotional piano chord progression', 'passionate male vocal', 'low tom roll', 'soft crash cymbal', 'heartfelt', 'romantic', 'emotional', 'passionate']"}} |
-tKZOl4q1Kw.wav | [
{
"from": "User",
"value": "Please describe the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-tKZOl4q1Kw.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Assistant",
"value... | en | {"custom_metadata": {"aspect_list": "['high pitched synth', 'riser', 'fuzzy synth', 'motif', 'synth melody']"}} |
-taO6N-rxv4.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-taO6N-rxv4.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"v... | en | {"custom_metadata": {"aspect_list": "['rock music', 'tutorial', 'electric guitar', 'acoustic drums', 'sound effects', 'underwater', 'loud', 'generic', 'common sounding']"}} |
-tpq_bzSKes.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-tpq_bzSKes.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"v... | en | {"custom_metadata": {"aspect_list": "['parole', 'strings', 'upright bass', 'harp', 'male deep voice singing']"}} |
-uaTK8sa5Ms.wav | [
{
"from": "User",
"value": "Write a detailed description of the music, including the recording quality, musical instruments, and any other specific features.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-uaTK8sa5Ms.wav",
... | en | {"custom_metadata": {"aspect_list": "['country', 'banjo', 'acoustic piano', 'violin', 'upright bass', 'uptempo']"}} |
-w12aSkQ9No.wav | [
{
"from": "User",
"value": "What can you say about this music recording?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-w12aSkQ9No.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['female vocalist', 'slow tempo', 'soprano', 'intense cello', 'beseeching', 'imploring', 'classical music', 'western classical', 'opera singer', 'violins', 'brass band', 'story telling', 'passionate', 'emotional', 'pleading', 'opera', 'orchestra', 'lilting melody', 'expressive vocal... |
-w8maIWtnUk.wav | [
{
"from": "User",
"value": "What are the characteristics of this music?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-w8maIWtnUk.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistan... | en | {"custom_metadata": {"aspect_list": "['instrumental', 'jam', 'electric guitar', 'clean sound', 'effect pedal', 'echo', 'dreamy', 'trippy']"}} |
-wymN80CiYU.wav | [
{
"from": "User",
"value": "Analyze the music and describe what you hear",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/-wymN80CiYU.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['male singer', 'backup singers', 'guitar lead', 'medium tempo', 'steady drumming rhythm', 'string section playing rhythmically', 'cymbals crashing', 'slick percussion clicks', 'strong bass line', 'keyboard harmony', 'modern pop hits', 'emotional', 'romantic', 'together for ever', '... |
0-7PyzhzuYQ.wav | [
{
"from": "User",
"value": "Write down a complete breakdown of the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0-7PyzhzuYQ.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Ass... | en | {"custom_metadata": {"aspect_list": "['bluegrass', 'no singer', 'instrumental', 'banjo', 'mandolin', 'acoustic guitar', 'playful', 'joyful', 'uplifting', 'easygoing', 'rural', 'pastoral']"}} |
04NjXsLyCl4.wav | [
{
"from": "User",
"value": "Analyze the music and describe what you hear",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/04NjXsLyCl4.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Ass... | en | {"custom_metadata": {"aspect_list": "['r&b', 'e-guitar sound', 'cymbals', 'digital drums', 'chimes', 'slow tempo', 'amateur recording']"}} |
05JAmKFVy44.wav | [
{
"from": "User",
"value": "Please describe the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/05JAmKFVy44.wav",
"type": "audio",
"duration": 9.741,
"offset": null
},
{
"from": "Assistant",
"value"... | en | {"custom_metadata": {"aspect_list": "['low quality', 'kids song', 'distorted', 'crushed', 'noisy', 'mono', 'keys chords', 'low male vocal']"}} |
07FxCXxknY4.wav | [
{
"from": "User",
"value": "Write a detailed description of the music, including the recording quality, musical instruments, and any other specific features.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/07FxCXxknY4.wav",
... | en | {"custom_metadata": {"aspect_list": "['fingerstyle-guitar', 'acoustic guitar', 'medium tempo', 'classical atmosphere']"}} |
07xGXxIHOL4.wav | [
{
"from": "User",
"value": "What can you say about this music recording?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/07xGXxIHOL4.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Ass... | en | {"custom_metadata": {"aspect_list": "['male singer', 'slow tempo', 'romantic piano', 'ambient music', 'saxophone harmony', 'steady drumming', 'groovy bass line', 'r&b', 'soul', 'blues', 'jazz', 'complex harmony', 'syncopated', 'pleasant', 'romantic', 'emotional', 'sentimental', 'love song', 'wedding song', 'proposal so... |
08mf5GxT820.wav | [
{
"from": "User",
"value": "What are the characteristics of this music?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/08mf5GxT820.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Assi... | en | {"custom_metadata": {"aspect_list": "['techno', 'digital drums', 'synth lead sound', 'synth bass', 'feet stumping noises', 'amateur recording', 'dancing']"}} |
09lQmg2wvsY.wav | [
{
"from": "User",
"value": "What can you say about this music recording?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/09lQmg2wvsY.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['amateur recording', 'digital sounds', 'riser', 'atmospheric']"}} |
0DizopdPMBw.wav | [
{
"from": "User",
"value": "How would you describe this musical excerpt?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0DizopdPMBw.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['poprock', 'e-bass', 'e-guitars', 'acoustic drums', 'female singer', 'uptempo']"}} |
0EOQco76eXQ.wav | [
{
"from": "User",
"value": "Write down a complete breakdown of the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0EOQco76eXQ.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Ass... | en | {"custom_metadata": {"aspect_list": "['slow tempo', 'drum brushes percussions', 'inspiring', 'devotional', 'romantic', 'together forever', 'ambient room noises', 'poignant', 'jazz music', 'bass solo', 'piano accompaniment', 'jazz band', 'smooth jazz', 'live performance', 'church music', 'slow tempo', 'groovy solo', 'em... |
0EvpBtracsk.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0EvpBtracsk.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"v... | en | {"custom_metadata": {"aspect_list": "['rock', 'pop', 'e-guitar', 'e-bass', 'piano', 'female voice singing', 'synth', 'drums', 'song change', 'medium to uptempo']"}} |
0F-Z0zF1504.wav | [
{
"from": "User",
"value": "Describe this music in a few sentences.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0F-Z0zF1504.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Assistan... | en | {"custom_metadata": {"aspect_list": "['male vocalist', 'medium tempo', 'dulcet', 'sentimental', 'emotional', 'love song', 'melodic', 'world music', 'k-pop hips', 'youthful', 'young love', 'soft soothing', 'romantic piano', 'steady drumming', 'straightforward bass lines', 'chimes', 'atmospheric synthesiser', 'boy band',... |
0Gxn9FtaJFc.wav | [
{
"from": "User",
"value": "Summarize the music : genre, strings, mood, where can it be played, quality etc...",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0Gxn9FtaJFc.wav",
"type": "audio",
"duration": 10.008,
"o... | en | {"custom_metadata": {"aspect_list": "['rock music', 'male vocal', 'synth', 'piano', 'bass guitar', 'acoustic drums', 'slow', 'melancholic']"}} |
0HXYdGGKV2k.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0HXYdGGKV2k.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"v... | en | {"custom_metadata": {"aspect_list": "['banjo player', 'fast tempo', 'groovy music', 'love video performance', 'instrumental music', 'virtuoso', 'walking bass line', 'entertaining', 'love performance', 'soloist', 'country blue grass', 'entertaining', 'energetic', 'passionate', 'spirited', 'instrumentalist', 'poor audio ... |
0ISHZQJdeSw.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0ISHZQJdeSw.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"v... | en | {"custom_metadata": {"aspect_list": "['male vocalist', 'slow tempo', 'hip-hop', 'rap', 'progressive', 'vocal backup', 'youthful', 'funky snare drumming', 'digital beats', 'syncopated piano accompaniment', 'groovy bass line', 'synthesiser arrangements', 'persuasive', 'story telling', 'rhythmic patter', 'rhythmic speech'... |
0J_TdiZ3TKA.wav | [
{
"from": "User",
"value": "Write a detailed description of the music, including the recording quality, musical instruments, and any other specific features.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0J_TdiZ3TKA.wav",
... | en | {"custom_metadata": {"aspect_list": "['male vocalist', 'fast tempo', 'foreign language', 'pleasant', 'soft', 'popular songs for children', 'animation', 'cartoon', 'adorable', 'cute', 'minimalist', 'vocal emphasisengaging', 'charming', 'animated singing', 'spirited piano accompaniment', 'fun', 'cheerful', 'sweet', 'catc... |
0JbGxIR8JTk.wav | [
{
"from": "User",
"value": "How would you describe this musical excerpt?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0JbGxIR8JTk.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['acoustic-electric nylon string guitar', 'fingerpicking', 'afrobeat', 'carribean', 'various african percussion', 'male singer', 'electric bass', 'syncopated drumset', 'free singing']"}} |
0KCVgexi4yU.wav | [
{
"from": "User",
"value": "Summarize the music : genre, strings, mood, where can it be played, quality etc...",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0KCVgexi4yU.wav",
"type": "audio",
"duration": 10,
"offse... | en | {"custom_metadata": {"aspect_list": "['amateur recording', 'electro', 'female voice singing', 'bass', 'digital drums', 'digital strings', 'upbeat']"}} |
0L2ndtt60Q8.wav | [
{
"from": "User",
"value": "What can you say about this music recording?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0L2ndtt60Q8.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['sound effects', 'chipmunk vocal', 'hamster', 'electronic music', 'comedy', 'parody', 'funny', 'high-pitch']"}} |
0LE6Ll1rVlg.wav | [
{
"from": "User",
"value": "Please describe the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0LE6Ll1rVlg.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"value": "... | en | {"custom_metadata": {"aspect_list": "['rock', 'passionate male vocal', 'harmonizing male vocals', 'wide electric guitar melody', 'groovy bass', 'punchy kick', 'punchy snare', 'shimmering cymbals', 'energetic', 'addictive']"}} |
0LLlcPiatiU.wav | [
{
"from": "User",
"value": "Write a detailed description of the music, including the recording quality, musical instruments, and any other specific features.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0LLlcPiatiU.wav",
... | en | {"custom_metadata": {"aspect_list": "['song fade', 'instrumental music', 'camera flash sounds', 'end credits music background', 'camera clicking tones', 'hip hop music', 'male singer', 'medium tempo', 'horns playing', 'fanfare', 'keyboard arpeggiated tones', 'slick drumming rhythm', 'groovy bass line', 'song ending', '... |
0MzrXd8CUCg.wav | [
{
"from": "User",
"value": "Give me a report on the music played",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0MzrXd8CUCg.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['wide resonating woodwind melody', 'noisy', 'audio crackles', 'loud', 'harsh', 'low quality']"}} |
0OY8XXZ98rw.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0OY8XXZ98rw.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"v... | en | {"custom_metadata": {"aspect_list": "['metal', 'double pedal kick', 'punchy snare', 'shimmering cymbals', 'distorted flat male vocal', 'wide aggressive electric guitar riff', 'distorted bass guitar', 'energetic', 'aggressive', 'distorted', 'manic']"}} |
0OYlHvyfNk4.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0OYlHvyfNk4.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['ska', 'acoustic guitars', 'shaker', 'e-bass', 'acoustic drums', 'male voice singing/rapping', 'male backing voices', 'uptempo']"}} |
0Olm321vgk8.wav | [
{
"from": "User",
"value": "What are the characteristics of this music?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0Olm321vgk8.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistan... | en | {"custom_metadata": {"aspect_list": "['low quality', 'r&b/soul', 'passionate echoing male vocal', 'punchy kick', 'punchy snare', 'electric guitar arpeggiated melody', 'fat bass guitar', 'people chattering', 'reverberant', 'live performance']"}} |
0PMFAO4TIU4.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0PMFAO4TIU4.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"v... | en | {"custom_metadata": {"aspect_list": "['new ethiopian music', 'digital drums', 'male voice sample', 'accordion-like sound', 'e-bass', 'medium tempo', 'uplifting energy']"}} |
0RcMzUdXDRQ.wav | [
{
"from": "User",
"value": "What are the characteristics of this music?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0RcMzUdXDRQ.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistan... | en | {"custom_metadata": {"aspect_list": "[\"children's song\", 'female vocal', 'acoustic guitar', 'electric guitar', 'bass guitar', 'acoustic guitar', 'repeated theme', 'acoustic drums', 'simple', 'easygoing', 'playful', 'medium tempo']"}} |
0RgGrVklaao.wav | [
{
"from": "User",
"value": "How would you describe this musical excerpt?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0RgGrVklaao.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['instrumental', 'medium tempo', 'sound of rain', 'anticipation', 'scary', 'dark', 'buzzing electric circuit', 'intense', 'suspense', 'thunder', 'lightening', 'metal clanging rhythmically', 'storm', 'thunder storm', 'rain storm', 'heavy rain', 'electronic music', 'two tracks', 'unre... |
0SNhAKyXtC8.wav | [
{
"from": "User",
"value": "Please describe the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0SNhAKyXtC8.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"value": "... | en | {"custom_metadata": {"aspect_list": "['oriental', 'harp', 'low and high frequencies', 'medium tempo']"}} |
0SnjS2w_c80.wav | [
{
"from": "User",
"value": "Tell me about the music you hear.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0SnjS2w_c80.wav",
"type": "audio",
"duration": 10.008,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['alternative', 'vocoder', 'keyboard', 'acoustic drums', 'unique', 'trippy']"}} |
0TV9zvfwFhs.wav | [
{
"from": "User",
"value": "Write a detailed description of the music, including the recording quality, musical instruments, and any other specific features.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0TV9zvfwFhs.wav",
... | en | {"custom_metadata": {"aspect_list": "['male voice', 'male backing vocals', 'r&b genre', 'electric piano', 'drums', 'bass guitar', 'tubular bell']"}} |
0TiEO149Ydc.wav | [
{
"from": "User",
"value": "Give me a report on the music played",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0TiEO149Ydc.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['low quality', 'noisy', 'alternative/indie', 'wooden percussive element', 'acoustic guitar strummed chord', 'passionate female vocal', 'emotional', 'passionate', 'live performance', 'unbalanced stereo image']"}} |
0Ubu4BqSWmU.wav | [
{
"from": "User",
"value": "Analyze the music and describe what you hear",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0Ubu4BqSWmU.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['male singer', 'slow tempo', 'funky bass lines', 'intense drumming', 'synthesiser arrangements', 'vocal backup', 'hip-hop', 'rap', 'pop rap', 'hip-hop hits', 'disco rap', 'rhythmic speech', 'story telling', 'passionate', 'emotional', 'persuasive', 'compelling', 'engaging', 'persuas... |
0VjPCd62oKg.wav | [
{
"from": "User",
"value": "Describe this music in a few sentences.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0VjPCd62oKg.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['instrumental', 'sound of water', 'water splashing', 'mind stimulating', 'songs for toddlers', 'kindergarten', 'songs for toddlers', 'animal sounds', 'learning about animals', 'duck song', 'ducks', 'song end', 'animated song', 'children’s music', 'children’s song', 'educational', '... |
0XxinBtKouQ.wav | [
{
"from": "User",
"value": "Analyze the music and describe what you hear",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0XxinBtKouQ.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['male vocalists', 'fast tempo', 'cheerful', 'happy', 'acoustic guitar', 'vigorous banjo', 'auto harp', 'mandolin', 'ambient noises', 'clapping', 'cheering', 'people talking', 'live performance', 'gig', 'concert', 'cheering', 'country music', 'country folk music', 'bluegrass', 'infe... |
0_XItMAYkwc.wav | [
{
"from": "User",
"value": "What are the characteristics of this music?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0_XItMAYkwc.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistan... | en | {"custom_metadata": {"aspect_list": "['rock/pop', 'e-guitars', 'e-bass', 'acoustic drums', 'male voices singing', 'higher register', 'uptempo']"}} |
0a91szM1Ivw.wav | [
{
"from": "User",
"value": "Write down a complete breakdown of the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0a91szM1Ivw.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['low quality', 'distorted passionate female vocal', 'noisy', 'live performance', 'traditional', 'emotional', 'subtle sitar melody', 'folk']"}} |
0abzD7hBTRk.wav | [
{
"from": "User",
"value": "Please describe the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0abzD7hBTRk.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"value": "... | en | {"custom_metadata": {"aspect_list": "['vocalisation', 'medium fast tempo', 'male vocalist', 'punchy', 'boomy', 'buoyant', 'rap', 'dance groove', 'vocal percussionist', 'youthful', 'rhythmic', 'skilled', 'engaging', 'beat boxing', 'turn table imitation', 'vigorous', 'youthful', 'vocal percussion', 'vocal turntablism', '... |
0bP2MH3LqvI.wav | [
{
"from": "User",
"value": "Describe this music in a few sentences.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0bP2MH3LqvI.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['piano music', 'no percussion', 'propeller sound', 'male narrative voice at the end', 'moderate tempo']"}} |
0bRUkLsttto.wav | [
{
"from": "User",
"value": "Please describe the music",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0bRUkLsttto.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
"value": "... | en | {"custom_metadata": {"aspect_list": "['hip-hop', 'male vocals', 'rapping', 'repeated theme', 'keyboard', 'synth bass', 'electronic drums', 'simple', 'groovy', 'dance', 'loud']"}} |
0bvPjMQ_WbE.wav | [
{
"from": "User",
"value": "Write a detailed description of the music, including the recording quality, musical instruments, and any other specific features.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0bvPjMQ_WbE.wav",
... | en | {"custom_metadata": {"aspect_list": "['low quality', 'live performance', 'loud steel pans melody', 'playback instrumental', 'shimmering hi hats', 'open hats', '4 on the floor kick', 'energetic', 'crowd talking', 'exotic']"}} |
0c1YU_VtFRE.wav | [
{
"from": "User",
"value": "Give me a report on the music played",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0c1YU_VtFRE.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assistant",
... | en | {"custom_metadata": {"aspect_list": "['acoustic piano', 'background-noises', 'wind', 'amateur recording', 'upbeat']"}} |
0cNYPgD6cEA.wav | [
{
"from": "User",
"value": "Write a detailed description of the music, including the recording quality, musical instruments, and any other specific features.",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0cNYPgD6cEA.wav",
... | en | {"custom_metadata": {"aspect_list": "['country/pop/singersongwriter', 'acoustic guitar', 'male singer', 'emotional', 'soulful']"}} |
0dPx94RPy2M.wav | [
{
"from": "User",
"value": "How would you describe this musical excerpt?",
"type": "text",
"duration": null,
"offset": null
},
{
"from": "User",
"value": "audio/music/MusicCaps/0dPx94RPy2M.wav",
"type": "audio",
"duration": 10,
"offset": null
},
{
"from": "Assista... | en | {"custom_metadata": {"aspect_list": "['advertisement', 'jingle', 'drill sounds', 'rock music', 'instrumental', 'electric guitar', 'keyboard', 'acoustic sounding drums', 'generic', 'simple tune']"}} |
Luciole Audio Evaluation Dataset
Dataset description
Luciole Audio Evaluation Dataset is the held-out evaluation collection used to benchmark the OpenLLM-France Luciole audio-language models. It is the evaluation counterpart of the Luciole Audio Training Dataset: a multilingual, multi-task set of audio–text conversations, restricted to the test splits of each source dataset, covering transcription, speech translation, spoken and music question answering, music captioning, speaker attributes (gender, age, emotion), spoken language identification, temporal localization, format following, and speaker diarization.
Each record is one evaluation example: the user turn(s) hold the instruction and the audio, and the assistant turn holds the reference (gold) answer to score against.
The repository holds only the text and metadata (the conversations and their references to audio files). The audio itself is not hosted on the Hub — see Getting the audio.
⚠️ Licensing / redistribution. This dataset aggregates many source datasets under different licenses. See Datasets and licenses: every split maps to exactly one source dataset, with its license and where its audio can be obtained. Datasets whose license forbids redistribution (e.g. NoDerivatives, or research-only agreements) are not included here and must be obtained from their original source.
Dataset structure
Luciole-Audio-Evaluation-Dataset/
├── README.md
├── dataset_stats.csv # per-split #examples / #audio / hours / license / audio_hosted
├── dataset_index.json # split → source dataset, license, provenance
└── data/ # the conversations (this is what lives on the Hub)
├── speech/ (asr, ast, qa, summarization, diarization, temporal, format_following,
│ emotion_reco, gender_reco, age_reco, language_reco)
└── music/ (qa, captioning)
The two top levels are <domain>/<task> (e.g. speech/asr, music/qa). Each
<domain>/<task> is exposed as the configuration <domain>.<task>, and each
source dataset (per language) is a split within it. For example, French ASR from
FLEURS is the FLEURS_fr split of the speech.asr config.
Data fields
Every record, in every split, has exactly these four fields:
| field | type | description |
|---|---|---|
id |
string | unique example id. |
conversations |
list | the dialogue turns (see below). |
language |
string | "fr", "en", … ; "multilingual" for language-identification; for translation, source-target like "fr-en". |
extra |
string | a JSON-serialized object with any extra source metadata; "{}" when there is none. |
Each turn in conversations has:
| field | type | description |
|---|---|---|
from |
string | "User" or "Assistant" |
type |
string | "text" or "audio" |
value |
string | the text (for the assistant turn, the reference answer), or a relative path to an audio file (for type: "audio") |
duration |
float | audio length in seconds (audio turns only; null otherwise) |
offset |
float | start offset in the audio file, in seconds (when the turn uses a segment; null otherwise) |
The reference answer to score against is the Assistant turn's value.
Audio is referenced by a relative path of the form audio/<domain>/<Dataset>/<file>,
task-independent, with the audio's own language in <Dataset> for speech
(FLEURS_fr, …) but not for music.
Example record (FLEURS fr ASR):
{
"id": "1829",
"conversations": [
{"from": "User", "value": "Écris le texte de cet enregistrement.", "type": "text"},
{"from": "User", "value": "audio/speech/FLEURS_fr/7105431834829365765.wav", "type": "audio", "duration": 9.42},
{"from": "Assistant", "value": "Les voyageurs à destination de pays où les taxes sont élevées …", "type": "text"}
],
"language": "fr",
"extra": "{\"dataset_name\": \"fleurs\"}"
}
Tasks
The evaluation covers the following tasks, organised by domain as <domain>/<task> (each
exposed as the configuration <domain>.<task>). Most instruction prompts were generated
by OpenLLM-France; the marks in the Datasets and licenses table
flag, per task line, where OpenLLM-France produced the audio (🎙️) or the text (✍️).
Speech
asr— Automatic Speech Recognition (FLEURS, Common Voice, VoxPopuli, SUMM-RE).ast— Automatic Speech Translation (source-target pairs, e.g.fr-en).qa— Spoken Question Answering (VoxPopuli-QA, Aya, Vigogne, National Speech Corpus, SpokenWOZ).summarization— Dialogue Summarization (National Speech Corpus SDS).temporal— Temporal Localization: word↔time queries (SLUE-SQA-5).format_following— Format Following: produce the answer in a required (e.g. JSON) format (SLUE-SQA-5).language_reco— Spoken Language Identification (CoVoST 2).emotion_reco— Emotion Recognition (MELD).gender_reco— Speaker Gender Recognition (Common Voice).age_reco— Speaker Age Recognition (Common Voice).diarization— Speaker Diarization ("who spoke when", with timestamps; AMI).
Music
qa— Music Question Answering (MusicCaps, MTG-Jamendo).captioning— Music Captioning (MusicCaps).
Loading
Because each <domain>/<task> is a separate config, load a config and pick a split:
from datasets import load_dataset
asr = load_dataset("OpenLLM-France/Luciole-Audio-Evaluation-Dataset", "speech.asr")
fleurs_fr = load_dataset("OpenLLM-France/Luciole-Audio-Evaluation-Dataset",
"speech.asr", split="FLEURS_fr")
See dataset_stats.csv for the size of every split and
dataset_index.json for the exact source dataset/license behind each.
Getting the audio
The audio is not part of this Hub repository. Most of it is served separately at:
https://dl.labs.linagora.com/files/datasets/OpenLLM-France/Luciole-Audio-Evaluation-Dataset/audio/
Download that audio/ folder and place it next to data/; its layout mirrors the audio
paths in the records (audio/<domain>/<Dataset>/…).
Some datasets' audio is not redistributable by us (copyrighted source, YouTube-only, NoDerivatives, or research-only agreements). For those, the conversations are still published (when permitted) but you must download the audio from the original source listed below. See Audio availability.
Datasets and licenses
This dataset is an aggregation of third-party datasets, each under its own license. The table below lists every source dataset used, its license, what is published here, where to get the audio, and its content (examples and audio duration, per task and language).
The instruction prompts (the user-turn wording that states each task) were written by OpenLLM-France for every task except question answering (qa).
Marks in the Content column flag data produced by OpenLLM-France, on the specific task line(s) concerned: 🎙️ = audio synthesized by OpenLLM-France · ✍️ = text (questions/answers, translations, or captions) generated or modified by OpenLLM-France — see each dataset's note below for details.
| Dataset | License | In this release | Audio | Content |
|---|---|---|---|---|
| AMI Meeting Corpus | CC-BY-4.0 | ✓ text + audio | hosted | 1,326 samples · 16h — ✍️ diarization, en |
| aya_collection | Apache-2.0 (text) Synthesized by OpenLLM-France (audio) |
✓ text + audio | hosted | 31 samples · 2min — 🎙️ qa, fr |
| Common Voice | CC0-1.0 | ✓ text + audio | hosted | 40,209 samples · 66h • asr, en — 16,401 · 27h • asr, fr — 16,186 · 26h • ✍️ gender_reco, en — 2,290 · 3h42 • ✍️ age_reco, en — 2,077 · 3h21 • ✍️ gender_reco, fr — 1,758 · 2h48 • ✍️ age_reco, fr — 1,497 · 2h23 |
| CoVoST2 (via AIR-Bench) | CC0-1.0 | ✓ text + audio | hosted | 1,000 samples · 1h35 — language_reco, multilingual |
| Fisher (via AIR-Bench) | LDC User Agreement (text) Copyrighted / LDC-restricted (audio) |
✗ excluded (external only) | source | qa, en |
| FLEURS | CC-BY-4.0 | ✓ text + audio | hosted | 5,654 samples · 19h • asr, pt — 913 · 3h11 • asr, es — 908 · 3h05 • asr, it — 862 · 3h30 • asr, de — 858 · 3h08 • asr, fr — 676 · 1h57 • asr, en — 645 · 1h46 • asr, ar — 428 · 1h18 • asr, nl — 364 · 58min |
| MELD | GPL-3.0 (text) Copyrighted (audio) |
✓ text only | source | 5,220 samples · 4h55 • emotion_reco, en — 2,610 · 2h27 • emotion_reco, fr — 2,610 · 2h27 |
| MTJ-Jamendo (via AIR-Bench) | CC-BY-NC-SA-4.0 (text) Mixed per-track CC (audio) |
✓ text only | source | 3,000 samples · 187h — music.qa, en |
| Multilingual TEDx | CC-BY-NC-ND-4.0 | ✗ excluded (external only) | source | 0 samples • asr, ar • asr, de • asr, es • asr, fr • asr, it • asr, pt • ast, es-fr • ast, es-it • ast, fr-en • ast, fr-es |
| MusicCaps | CC-BY-SA-4.0 (text) Copyrighted (audio) |
✓ text only | source | 8,316 samples · 23h • music.captioning, en — 2,772 · 7h42 • ✍️ music.qa, en — 2,772 · 7h42 • ✍️ music.qa, fr — 2,772 · 7h42 |
| National Speech Corpus | Singapore Open Data Licence v1.0 | ✓ text + audio | hosted | 700 samples · 5h24 • qa, en — 400 · 3h05 • summarization, en — 300 · 2h19 |
| SLUE-SQA-5 (SLUE phase-2) | Apache-2.0 / CC-BY-SA-4.0 | ✓ text + audio | hosted | 1,162 samples · 13h • ✍️ temporal, en — 797 · 8h49 • ✍️ format_following, en — 365 · 4h02 |
| SpokenWOZ (via AIR-Bench) | CC-BY-NC-4.0 | ✓ text + audio | hosted | 193 samples · 1h25 — qa, en |
| SUMM-RE | CC-BY-SA-4.0 | ✓ text + audio | hosted | 17,121 samples · 12h — asr, fr |
| Vigogne (French Alpaca) | CC-BY-NC-4.0 (text) Synthesized by OpenLLM-France (audio) |
✓ text + audio | hosted | 502 samples · 47min — 🎙️ qa, fr |
| VoxPopuli | CC0-1.0 | ✓ text + audio | hosted | 3,584 samples · 9h49 • asr, en — 1,842 · 4h55 • asr, fr — 1,742 · 4h53 |
| VoxPopuli-QA | CC0-1.0 (text) Synthesized by OpenLLM-France (audio) |
✓ text + audio | hosted | 570 samples · 4h34 — 🎙️ qa, fr |
| YouTubeFr | Copyrighted | ✗ excluded (external only) | source | asr, fr |
Audio availability
Where to obtain the audio for each source dataset, grouped by what is published in this repository.
Text and audio
Both the conversations and the audio are published. The audio is hosted at https://dl.labs.linagora.com/files/datasets/OpenLLM-France/Luciole-Audio-Evaluation-Dataset/audio/; each record's audio path is relative to that folder.
- AMI Meeting Corpus — CC-BY-4.0 — hosted
AMI meeting recordings (CC-BY-4.0). Speaker-diarization evaluation: OpenLLM-France generated the prompts and assembled the reference "who spoke when" timelines.
Source: AMI Meeting Corpus (University of Edinburgh) — CC-BY-4.0 — https://groups.inf.ed.ac.uk/ami/corpus/ - aya_collection — Apache-2.0 (text), Synthesized by OpenLLM-France (Chatterbox TTS) (audio) — hosted
French QA from the Aya Collection (Apache-2.0). The spoken questions were synthesized by OpenLLM-France (Chatterbox TTS).
Source: [text] Aya Collection (Cohere Labs) — Apache-2.0 — https://huggingface.co/datasets/CohereLabs/aya_collection - Common Voice — CC0-1.0 — hosted
Mozilla Common Voice (CC0-1.0). Used for ASR (generated prompts) and for speaker gender/age recognition, where OpenLLM-France generated the prompts and assembled the answer phrasings from Common Voice metadata.
Source: Mozilla Common Voice — CC0-1.0 — https://commonvoice.mozilla.org/en/datasets - CoVoST2 (via AIR-Bench) — CC0-1.0 — hosted
CoVoST 2 (audio derived from Common Voice, CC0), used for spoken language identification via AIR-Bench.
Source: CoVoST 2 (audio from Common Voice, CC0) — CC0-1.0 — https://github.com/facebookresearch/covost - FLEURS — CC-BY-4.0 — hosted
Multilingual read speech (FLoRes-based). Evaluation prompts generated by OpenLLM-France; the reference transcripts are the original FLEURS data (CC-BY-4.0).
Source: FLEURS (Google) — CC-BY-4.0 — https://huggingface.co/datasets/google/fleurs - National Speech Corpus — Singapore Open Data Licence v1.0 — hosted
Singapore IMDA National Speech Corpus, used for spoken QA (SQA) and dialogue summarization (SDS) via the AudioLLMs repackaging. Distributed under the Singapore Open Data Licence v1.0 (redistribution permitted with attribution). [Confidence: medium — IMDA page unreachable at audit time; AudioLLMs repo is access-gated.]
Sources:- IMDA National Speech Corpus (Singapore) — Singapore Open Data Licence v1.0 — https://www.imda.gov.sg/how-we-can-help/national-speech-corpus
- AudioLLMs Multitask National Speech Corpus (repackaging) — Singapore Open Data Licence v1.0 — https://huggingface.co/datasets/AudioLLMs
- SLUE-SQA-5 (SLUE phase-2) — Apache-2.0 / CC-BY-SA-4.0 — hosted
SLUE-SQA-5, used for temporal localization (time2word/word2time) and JSON-format following. OpenLLM-France generated the prompts and assembled the reference answers.
Source: SLUE-SQA-5 (SLUE phase-2) — Apache-2.0 / CC-BY-SA-4.0 — https://huggingface.co/datasets/asapp/slue-phase-2 - SpokenWOZ (via AIR-Bench) — CC-BY-NC-4.0 — hosted
Task-oriented spoken dialogue (CC-BY-NC-4.0, first-party recordings), used for spoken QA via AIR-Bench. Non-commercial.
Source: SpokenWOZ (Alibaba DAMO / Tianjin Univ.) — CC-BY-NC-4.0 — https://spokenwoz.github.io/ - SUMM-RE — CC-BY-SA-4.0 — hosted
French meeting corpus by LINAGORA (CC-BY-SA-4.0, first-party recordings). ASR evaluation prompts generated by OpenLLM-France. ShareAlike: this subset stays CC-BY-SA-compatible.
Source: SUMM-RE (LINAGORA) — CC-BY-SA-4.0 — https://huggingface.co/datasets/linagora/SUMM-RE - Vigogne (French Alpaca) — CC-BY-NC-4.0 (text), Synthesized by OpenLLM-France (Chatterbox TTS) (audio) — hosted
French instruction QA (Vigogne/Alpaca, CC-BY-NC-4.0). The spoken questions were synthesized by OpenLLM-France (Chatterbox TTS).
Source: [text] Vigogne / Alpaca (French) — CC-BY-NC-4.0 — https://github.com/bofenghuang/vigogne - VoxPopuli — CC0-1.0 — hosted
European Parliament recordings (CC0-1.0). ASR evaluation prompts generated by OpenLLM-France.
Source: VoxPopuli (European Parliament) — CC0-1.0 — https://github.com/facebookresearch/voxpopuli - VoxPopuli-QA — CC0-1.0 (transcripts; Q&A by OpenLLM-France) (text), Synthesized by OpenLLM-France (Chatterbox TTS) (audio) — hosted
Spoken QA over VoxPopuli (CC0). OpenLLM-France synthesized the spoken questions (Chatterbox TTS) and generated the question/answer text.
Source: [text] VoxPopuli transcripts (source) — CC0-1.0 — https://github.com/facebookresearch/voxpopuli
Text only
The conversations are published here, but the audio is not redistributable by us — download it from the original source(s):
- MELD — GPL-3.0 (text), Copyrighted (Friends TV series) (audio) — source
Multimodal emotion dataset from the Friends TV series. Emotion-recognition evaluation prompts generated by OpenLLM-France; the audio is copyrighted TV content and is not hosted here.
Source: [text] MELD (annotations) — GPL-3.0 — https://affective-meld.github.io/ - MTJ-Jamendo (via AIR-Bench) — CC-BY-NC-SA-4.0 (metadata) (text), Mixed per-track CC (Jamendo) — authorization required (audio) — source
Music tagging/QA over Jamendo tracks via AIR-Bench. Metadata is CC-BY-NC-SA-4.0; the audio has mixed per-track CC licenses plus a Jamendo clause requiring prior written authorization for redistribution, so the audio is not hosted here.
Sources:- [text] MTG-Jamendo (tags/metadata) — CC-BY-NC-SA-4.0 — https://github.com/MTG/mtg-jamendo-dataset
- [audio] Jamendo tracks (per-track CC; non-commercial research clause) — Mixed CC / Jamendo authorization — https://github.com/MTG/mtg-jamendo-dataset
- MusicCaps — CC-BY-SA-4.0 (text), Copyrighted (YouTube / music industry rights) (audio) — source
Music captioning + QA over MusicCaps clips (captions CC-BY-SA-4.0; audio is copyrighted YouTube content, not hosted). OpenLLM-France generated the English music Q&A from the captions and translated the French Q&A; captioning prompts were generated.
Sources:- [text] MusicCaps (captions) — CC-BY-SA-4.0 — https://www.kaggle.com/datasets/googleai/musiccaps
- [audio] YouTube / AudioSet (underlying music) — Copyrighted — https://research.google.com/audioset/
For YouTube-sourced audio (e.g. MusicCaps, YouTubeFr): the original video/clip ID is preserved in the audio file name (and in each record's extra field). Fetch the audio from YouTube with the source dataset's tooling or a downloader such as yt-dlp, then cut each segment using the offset / duration of the corresponding audio turn.
Not included
Neither the audio nor the conversations are published (the license forbids redistribution) — get the whole dataset from the source(s):
- Fisher (via AIR-Bench) — LDC User Agreement (research-only) (text), Copyrighted / LDC-restricted (audio) — source
Fisher English telephone speech, distributed by LDC under a non-transferable research-only agreement; neither audio nor transcripts may be redistributed. NOT included here. Obtain from LDC.
Source: Fisher English Training Speech (LDC2004S13 / LDC2005S13) — LDC User Agreement for Non-Members (research-only) — https://catalog.ldc.upenn.edu/LDC2004S13 - Multilingual TEDx — CC-BY-NC-ND-4.0 — source
TEDx talks for ASR and speech translation. The license is CC-BY-NC-ND-4.0: NoDerivatives forbids redistributing our re-segmented/reformatted version, so it is NOT included here (as in the training set). Obtain from the source. [DECISION FLAGGED: publishing eval references would be a derivative.]
Source: Multilingual TEDx (OpenSLR 100) — CC-BY-NC-ND-4.0 — https://www.openslr.org/100/ - YouTubeFr — Copyrighted (YouTube) — source
French YouTube speech. The audio is copyrighted YouTube content, so it is NOT included here (as in the training set). [DECISION FLAGGED.]
Source: YouTube (source videos) — Copyrighted (YouTube) — https://www.youtube.com/
Licensing
No single license covers the whole collection — it is a collection in which each source dataset retains its own license (see the table above). The curator's added layer (the evaluation prompts, the assembled reference answers, and the formatting) and the collection as a whole are offered under CC-BY-NC-SA-4.0, the most permissive single license consistent with the NonCommercial + ShareAlike terms of the included sources.
NoDerivatives (ND) and research-only sources (e.g. Multilingual TEDx, Fisher) may not be redistributed here; YouTube/broadcast-sourced audio (e.g. MELD, MusicCaps) is not hosted. Download those from their original source (see the table).
When in doubt, comply with the most restrictive applicable terms for the subset you use. If you are a rights holder and believe something should not be included, please open an issue.
Attribution
This dataset builds on the work of many others. Several sources are under attribution (CC-BY)* licenses and require credit. Please attribute every source dataset you use; the attribution-required ones are highlighted here:
The following datasets carry a CC-BY / attribution license on their text and/or audio — you must credit them (and cite their papers) when you use this dataset:
- AMI Meeting Corpus (CC-BY-4.0) — source
- FLEURS (CC-BY-4.0) — source
- MTJ-Jamendo (via AIR-Bench) (CC-BY-NC-SA-4.0 (metadata) (text), Mixed per-track CC (Jamendo) — authorization required (audio)) — source
- MusicCaps (CC-BY-SA-4.0 (text), Copyrighted (YouTube / music industry rights) (audio)) — source
- SLUE-SQA-5 (SLUE phase-2) (Apache-2.0 / CC-BY-SA-4.0) — source
- SpokenWOZ (via AIR-Bench) (CC-BY-NC-4.0) — source
- SUMM-RE (CC-BY-SA-4.0) — source
- Vigogne (French Alpaca) (CC-BY-NC-4.0 (text), Synthesized by OpenLLM-France (Chatterbox TTS) (audio)) — source
These also require keeping their text license/attribution notice (Apache-2.0 / MIT / CDLA):
Citation
If you use this dataset, please cite the OpenLLM-France / Luciole project and the individual source datasets you rely on (see the table above for sources).
Acknowledgements
Built by LINAGORA / OpenLLM-France. This evaluation collection would not exist without the authors of the many source datasets it builds upon.
- Downloads last month
- -