Random118's picture
Add Russian CosyVoice 3 dubbing pack and audio gallery
8c2913a verified
Raw History Blame Contribute Delete
3.56 kB
{
"file": "references/0046.wav",
"sample_rate_for_analysis": 16000,
"duration_sec": 3.858,
"voiced_fraction": 0.746,
"pause_map": [
{
"start": 1.06,
"end": 1.19,
"duration": 0.13
},
{
"start": 1.79,
"end": 1.91,
"duration": 0.12
}
],
"f0_hz": {
"median": 175.04,
"p10_p90": [
138.528,
209.969
],
"contour_20_points": [
243.99,
223.35,
162.07,
140.95,
170.41,
195.31,
218.82,
208.76,
205.17,
199.31,
174.59,
197.46,
154.9,
146.77,
209.1,
184.91,
146.86,
140.48,
136.15,
108.69
]
},
"energy_db": {
"p10_p50_p90": [
-49.24,
-14.599,
-8.273
],
"dynamic_range_db": 40.967,
"contour_20_points": [
-77.93,
-9.55,
-14.4,
-12.18,
-18.56,
-15.75,
-31.54,
-10.8,
-20.92,
-45.03,
-8.1,
-8.88,
-10.75,
-15.92,
-12.71,
-7.65,
-11.01,
-23.83,
-19.48,
-60.06
]
},
"timbral_proxies": {
"spectral_centroid_hz_median": 1766.239,
"spectral_flatness_median": 0.003
},
"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": "Прекратите сейчас — и торт подадут немедленно.",
"text_chars_per_sec": 11.923,
"source": {
"file": "sources_silero/0046.wav",
"sample_rate_for_analysis": 16000,
"duration_sec": 2.525,
"voiced_fraction": 0.747,
"pause_map": [],
"f0_hz": {
"median": 219.9,
"p10_p90": [
172.331,
251.143
],
"contour_20_points": [
212.41,
226.34,
236.26,
280.49,
247.05,
229.85,
237.41,
222.45,
228.95,
200.98,
255.07,
226.77,
189.81,
217.37,
223.47,
189.96,
174.16,
161.83,
196.47,
205.17
]
},
"energy_db": {
"p10_p50_p90": [
-42.716,
-22.267,
-15.447
],
"dynamic_range_db": 27.268,
"contour_20_points": [
-84.9,
-14.66,
-11.7,
-17.51,
-16.81,
-22.17,
-17.58,
-23.84,
-42.24,
-27.47,
-13.47,
-39.7,
-17.65,
-18.02,
-17.71,
-19.25,
-29.02,
-27.44,
-42.88,
-78.25
]
},
"timbral_proxies": {
"spectral_centroid_hz_median": 1444.414,
"spectral_flatness_median": 0.005
},
"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": "Прекратите сейчас — и торт подадут немедленно.",
"text_chars_per_sec": 18.218
},
"pipeline_control": {
"tts_text": "Прекратите сейчас — и торт подадут немедленно.",
"duration_stage": "pre",
"speaker_reference": "0046"
}
}