humaneness-ears-base-medium / gemini_burst_mapping.json
ChristophSchuhmann's picture
Release best Gemini-tuned Whisper Base and Small with code, normalization and evaluation
cd9b2d8 verified
Raw History Blame Contribute Delete
5.59 kB
{
"fine_to_group23": {
"Breathy Giggle": "laugh_soft",
"Cackle": "laugh_loud",
"Childlike Giggle": "laugh_soft",
"Chuckle": "laugh_soft",
"Guffaw": "laugh_loud",
"Nervous Giggle": "laugh_soft",
"Snicker": "laugh_soft",
"Snorting Giggle": "laugh_soft",
"Convulsive Sob": "sob",
"Mournful Wail": "wail",
"Quiet Sob": "sob",
"Sobs": "sob",
"Trembling Whimper": "sob",
"Deep Breath": "breath_calm",
"Deep Breathing": "breath_calm",
"Fast Breathing": "breath_fast",
"Heavy Breathing": "breath_fast",
"Normal Breathing": "breath_calm",
"Panting": "breath_fast",
"Slow Breathing": "breath_calm",
"Contented Sigh": "sigh_pos",
"Exasperated Sigh": "sigh_neg",
"Relief Sigh": "sigh_pos",
"Wistful Sigh": "sigh_pos",
"Fearful Gasp": "gasp",
"Sharp Inhale": "gasp",
"Surprised Gasp": "gasp",
"Exhausted Groan": "sigh_neg",
"Frustrated Groan": "sigh_neg",
"Pain Moan": "moan",
"Pleasure Moan": "moan",
"Affirmative Grunt": "grunt",
"Displeased Grunt": "sigh_neg",
"Effort Grunt": "grunt",
"Ahem": "throat",
"Clears Throat": "throat",
"Growl": "growl",
"Gurgling": "misc_body",
"Hiss": "hiss",
"Low Mumble": "hum",
"Whispered Mumble": "hum",
"Humming": "hum",
"Purr": "hum",
"Resonant Hum": "hum",
"Soft Hum": "hum",
"Cough": "throat",
"Coughing": "throat",
"Hiccup": "hiccup",
"Hiccups": "hiccup",
"Sniff": "sniff",
"Snort": "sniff",
"Yawn": "yawn",
"Person Whistling Playfully": "whistle",
"Person Whistling to Get Attention": "whistle",
"Sharp Whistle": "whistle",
"Soft Whistle": "whistle",
"Wolf Whistle": "whistle",
"Blowing a Kiss": "mouth",
"Kissing Noises": "mouth",
"Kissing Sounds": "mouth",
"Lip Smack": "mouth",
"Smack One's Lips": "mouth",
"Smacks Lips": "mouth",
"Licking Sound": "mouth",
"Spitting": "mouth",
"Sucking Noise": "mouth",
"Click One's Tongue": "mouth",
"Clicks Tongue": "mouth",
"Tongue Click": "mouth",
"Tsk": "mouth",
"Chewing Noises": "mouth",
"Drinking Noises": "swallow",
"Gulps": "swallow",
"Nervous Gulp": "swallow",
"Slurping Noises": "swallow",
"Swallows": "swallow",
"Scream": "scream",
"Shriek": "scream"
},
"fine_to_checkpoint_class": {
"Breathy Giggle": 4,
"Cackle": 5,
"Childlike Giggle": 6,
"Chuckle": 7,
"Guffaw": 18,
"Nervous Giggle": 27,
"Snicker": 38,
"Snorting Giggle": 41,
"Convulsive Sob": 0,
"Mournful Wail": 26,
"Quiet Sob": 30,
"Sobs": 0,
"Trembling Whimper": 48,
"Deep Breath": 3,
"Deep Breathing": 3,
"Fast Breathing": 3,
"Heavy Breathing": 3,
"Normal Breathing": 3,
"Panting": 0,
"Slow Breathing": 3,
"Contented Sigh": 8,
"Exasperated Sigh": 13,
"Relief Sigh": 31,
"Wistful Sigh": 51,
"Fearful Gasp": 15,
"Sharp Inhale": 33,
"Surprised Gasp": 44,
"Exhausted Groan": 14,
"Frustrated Groan": 16,
"Pain Moan": 0,
"Pleasure Moan": 0,
"Affirmative Grunt": 1,
"Displeased Grunt": 11,
"Effort Grunt": 12,
"Ahem": 2,
"Clears Throat": 46,
"Growl": 17,
"Gurgling": 0,
"Hiss": 0,
"Low Mumble": 25,
"Whispered Mumble": 50,
"Humming": 21,
"Purr": 29,
"Resonant Hum": 21,
"Soft Hum": 21,
"Cough": 9,
"Coughing": 9,
"Hiccup": 20,
"Hiccups": 20,
"Sniff": 39,
"Snort": 40,
"Yawn": 52,
"Person Whistling Playfully": 0,
"Person Whistling to Get Attention": 0,
"Sharp Whistle": 34,
"Soft Whistle": 42,
"Wolf Whistle": 0,
"Blowing a Kiss": 0,
"Kissing Noises": 22,
"Kissing Sounds": 22,
"Lip Smack": 24,
"Smack One's Lips": 0,
"Smacks Lips": 24,
"Licking Sound": 0,
"Spitting": 43,
"Sucking Noise": 0,
"Click One's Tongue": 0,
"Clicks Tongue": 47,
"Tongue Click": 47,
"Tsk": 49,
"Chewing Noises": 0,
"Drinking Noises": 0,
"Gulps": 19,
"Nervous Gulp": 28,
"Slurping Noises": 0,
"Swallows": 45,
"Scream": 32,
"Shriek": 35
},
"checkpoint_classes": [
"Other / rare burst",
"Affirmative Grunt",
"Ahem",
"Breath",
"Breathy Giggle",
"Cackle",
"Childlike Giggle",
"Chuckle",
"Contented Sigh",
"Cough",
"Crying",
"Displeased Grunt",
"Effort Grunt",
"Exasperated Sigh",
"Exhausted Groan",
"Fearful Gasp",
"Frustrated Groan",
"Growl",
"Guffaw",
"Gulp",
"Hiccup",
"Hum",
"Kissing Sound",
"Laughter",
"Lip Smack",
"Low Mumble",
"Mournful Wail",
"Nervous Giggle",
"Nervous Gulp",
"Purr",
"Quiet Sob",
"Relief Sigh",
"Scream",
"Sharp Inhale",
"Sharp Whistle",
"Shriek",
"Sigh",
"Sneeze",
"Snicker",
"Sniff",
"Snort",
"Snorting Giggle",
"Soft Whistle",
"Spitting",
"Surprised Gasp",
"Swallows",
"Throat Clearing",
"Tongue Click",
"Trembling Whimper",
"Tsk",
"Whispered Mumble",
"Wistful Sigh",
"Yawn"
],
"unrepresented_fine_classes": [
"Convulsive Sob",
"Sobs",
"Panting",
"Pain Moan",
"Pleasure Moan",
"Gurgling",
"Hiss",
"Person Whistling Playfully",
"Person Whistling to Get Attention",
"Wolf Whistle",
"Blowing a Kiss",
"Smack One's Lips",
"Licking Sound",
"Sucking Noise",
"Click One's Tongue",
"Chewing Noises",
"Drinking Noises",
"Slurping Noises"
]
}