Download Models/Russian_CosyVoice3/profiles/0208.json from Random118/GLaDOS_TTS: direct link, hf CLI and curl.
- Browser
- Download file 4.51 kB
-
https://huggingface.co/Random118/GLaDOS_TTS/resolve/main/Models/Russian_CosyVoice3/profiles/0208.json
- Command line
-
hf download hf://Random118/GLaDOS_TTS/Models/Russian_CosyVoice3/profiles/0208.json
-
curl -L -o 0208.json https://huggingface.co/Random118/GLaDOS_TTS/resolve/main/Models/Russian_CosyVoice3/profiles/0208.json
4.51 kB
| { | |
| "file": "references/0208.wav", | |
| "sample_rate_for_analysis": 16000, | |
| "duration_sec": 10.029, | |
| "voiced_fraction": 0.41, | |
| "pause_map": [ | |
| { | |
| "start": 1.28, | |
| "end": 1.37, | |
| "duration": 0.09 | |
| }, | |
| { | |
| "start": 1.68, | |
| "end": 2.26, | |
| "duration": 0.58 | |
| }, | |
| { | |
| "start": 2.62, | |
| "end": 2.77, | |
| "duration": 0.15 | |
| }, | |
| { | |
| "start": 3.46, | |
| "end": 3.73, | |
| "duration": 0.27 | |
| }, | |
| { | |
| "start": 5.22, | |
| "end": 5.44, | |
| "duration": 0.22 | |
| }, | |
| { | |
| "start": 5.92, | |
| "end": 6.24, | |
| "duration": 0.32 | |
| } | |
| ], | |
| "f0_hz": { | |
| "median": 185.984, | |
| "p10_p90": [ | |
| 115.817, | |
| 307.413 | |
| ], | |
| "contour_20_points": [ | |
| 169.57, | |
| 159.63, | |
| 263.36, | |
| 437.27, | |
| 356.17, | |
| 281.8, | |
| 243.33, | |
| 204.23, | |
| 212.08, | |
| 210.38, | |
| 274.54, | |
| 331.55, | |
| 388.57, | |
| 445.58, | |
| 479.6, | |
| 195.62, | |
| 164.29, | |
| 116.03, | |
| 121.02, | |
| 137.73 | |
| ] | |
| }, | |
| "energy_db": { | |
| "p10_p50_p90": [ | |
| -49.648, | |
| -15.552, | |
| -8.812 | |
| ], | |
| "dynamic_range_db": 40.836, | |
| "contour_20_points": [ | |
| -63.96, | |
| -8.35, | |
| -16.6, | |
| -9.47, | |
| -55.84, | |
| -44.47, | |
| -27.62, | |
| -57.49, | |
| -11.69, | |
| -29.76, | |
| -55.79, | |
| -24.67, | |
| -18.95, | |
| -12.51, | |
| -10.5, | |
| -9.1, | |
| -9.55, | |
| -12.14, | |
| -14.25, | |
| -55.53 | |
| ] | |
| }, | |
| "timbral_proxies": { | |
| "spectral_centroid_hz_median": 1982.711, | |
| "spectral_flatness_median": 0.025 | |
| }, | |
| "interpretation": { | |
| "target": "soft, close-mic, restrained mechanical delivery", | |
| "sarcasm": "low-to-moderate pitch movement with deliberate clause-final timing", | |
| "smile": "look for local energy/brightness lift around emphasized words; do not synthesize a broad cheerful smile" | |
| }, | |
| "text": "Нейротоксин... [кашель] [кашель] Такой смертельный... задыхаюсь... [смех] Шучу!", | |
| "text_chars_per_sec": 7.877, | |
| "source": { | |
| "file": "sources_silero/0208.wav", | |
| "sample_rate_for_analysis": 16000, | |
| "duration_sec": 6.425, | |
| "voiced_fraction": 0.557, | |
| "pause_map": [ | |
| { | |
| "start": 1.12, | |
| "end": 1.5, | |
| "duration": 0.38 | |
| }, | |
| { | |
| "start": 1.95, | |
| "end": 2.29, | |
| "duration": 0.34 | |
| }, | |
| { | |
| "start": 2.74, | |
| "end": 3.01, | |
| "duration": 0.27 | |
| }, | |
| { | |
| "start": 3.96, | |
| "end": 4.12, | |
| "duration": 0.16 | |
| }, | |
| { | |
| "start": 4.83, | |
| "end": 5.03, | |
| "duration": 0.2 | |
| }, | |
| { | |
| "start": 5.48, | |
| "end": 5.79, | |
| "duration": 0.31 | |
| } | |
| ], | |
| "f0_hz": { | |
| "median": 215.499, | |
| "p10_p90": [ | |
| 177.585, | |
| 260.452 | |
| ], | |
| "contour_20_points": [ | |
| 270.73, | |
| 247.77, | |
| 260.0, | |
| 170.01, | |
| 219.53, | |
| 206.14, | |
| 208.0, | |
| 243.0, | |
| 178.61, | |
| 219.47, | |
| 249.24, | |
| 180.74, | |
| 252.34, | |
| 255.04, | |
| 183.44, | |
| 236.06, | |
| 171.42, | |
| 235.98, | |
| 223.93, | |
| 194.78 | |
| ] | |
| }, | |
| "energy_db": { | |
| "p10_p50_p90": [ | |
| -71.844, | |
| -29.089, | |
| -15.943 | |
| ], | |
| "dynamic_range_db": 55.902, | |
| "contour_20_points": [ | |
| -77.92, | |
| -22.32, | |
| -17.29, | |
| -24.88, | |
| -60.0, | |
| -20.58, | |
| -60.13, | |
| -12.25, | |
| -32.96, | |
| -19.41, | |
| -14.99, | |
| -20.67, | |
| -63.99, | |
| -35.79, | |
| -31.51, | |
| -32.15, | |
| -32.38, | |
| -79.22, | |
| -21.52, | |
| -59.8 | |
| ] | |
| }, | |
| "timbral_proxies": { | |
| "spectral_centroid_hz_median": 1596.167, | |
| "spectral_flatness_median": 0.013 | |
| }, | |
| "interpretation": { | |
| "target": "soft, close-mic, restrained mechanical delivery", | |
| "sarcasm": "low-to-moderate pitch movement with deliberate clause-final timing", | |
| "smile": "look for local energy/brightness lift around emphasized words; do not synthesize a broad cheerful smile" | |
| }, | |
| "text": "Нейротоксин. Кашель. Кашель. Такой смертельный. Задыхаюсь. Смех. Шучу!", | |
| "text_chars_per_sec": 10.895 | |
| }, | |
| "pipeline_control": { | |
| "tts_text": "Нейротоксин. Кашель. Кашель. Такой смертельный. Задыхаюсь. Смех. Шучу!", | |
| "duration_stage": "pre", | |
| "speaker_reference": "0208" | |
| } | |
| } | |