Random118's picture
Add Russian CosyVoice 3 dubbing pack and audio gallery
8c2913a verified
Raw History Blame Contribute Delete
3.65 kB
{
"file": "references/0072.wav",
"sample_rate_for_analysis": 16000,
"duration_sec": 4.57,
"voiced_fraction": 0.803,
"pause_map": [
{
"start": 0.49,
"end": 0.73,
"duration": 0.24
}
],
"f0_hz": {
"median": 184.913,
"p10_p90": [
156.393,
217.126
],
"contour_20_points": [
241.19,
212.1,
188.46,
194.22,
207.56,
219.94,
222.45,
174.53,
175.55,
175.08,
195.91,
177.35,
177.19,
190.35,
211.19,
168.82,
165.56,
151.18,
129.25,
129.25
]
},
"energy_db": {
"p10_p50_p90": [
-38.226,
-13.668,
-9.139
],
"dynamic_range_db": 29.087,
"contour_20_points": [
-69.45,
-10.42,
-37.31,
-37.82,
-11.51,
-28.4,
-8.02,
-9.9,
-9.14,
-9.99,
-9.29,
-15.81,
-22.69,
-12.06,
-7.93,
-15.01,
-40.71,
-12.62,
-30.96,
-63.56
]
},
"timbral_proxies": {
"spectral_centroid_hz_median": 1702.818,
"spectral_flatness_median": 0.004
},
"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": "По завершении теста будут доступны торт и консультации по переживанию утраты.",
"text_chars_per_sec": 16.85,
"source": {
"file": "sources_silero/0072.wav",
"sample_rate_for_analysis": 16000,
"duration_sec": 4.088,
"voiced_fraction": 0.763,
"pause_map": [],
"f0_hz": {
"median": 209.969,
"p10_p90": [
181.736,
264.545
],
"contour_20_points": [
230.3,
223.16,
280.49,
230.82,
302.13,
209.26,
203.99,
261.51,
206.86,
228.63,
201.5,
198.36,
213.64,
203.25,
196.63,
184.91,
177.16,
173.36,
150.2,
150.2
]
},
"energy_db": {
"p10_p50_p90": [
-38.125,
-20.63,
-15.019
],
"dynamic_range_db": 23.105,
"contour_20_points": [
-83.4,
-15.96,
-17.03,
-14.32,
-19.54,
-23.35,
-17.84,
-17.96,
-38.46,
-36.89,
-18.82,
-23.22,
-21.69,
-35.59,
-19.55,
-20.26,
-22.11,
-22.33,
-33.64,
-77.39
]
},
"timbral_proxies": {
"spectral_centroid_hz_median": 1460.954,
"spectral_flatness_median": 0.006
},
"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": "По завершении теста будут доступны торт и консультации по переживанию утраты.",
"text_chars_per_sec": 18.838
},
"pipeline_control": {
"tts_text": "По завершении теста будут доступны торт и консультации по переживанию утраты.",
"duration_stage": "pre",
"speaker_reference": "0072"
}
}