Random118's picture
Add Russian CosyVoice 3 dubbing pack and audio gallery
8c2913a verified
Raw History Blame Contribute Delete
4.93 kB
{
"file": "references/0234.wav",
"sample_rate_for_analysis": 16000,
"duration_sec": 11.572,
"voiced_fraction": 0.565,
"pause_map": [
{
"start": 0.64,
"end": 0.92,
"duration": 0.28
},
{
"start": 1.35,
"end": 1.66,
"duration": 0.31
},
{
"start": 4.45,
"end": 5.73,
"duration": 1.28
},
{
"start": 8.42,
"end": 9.11,
"duration": 0.69
},
{
"start": 9.96,
"end": 10.72,
"duration": 0.76
}
],
"f0_hz": {
"median": 146.765,
"p10_p90": [
133.039,
187.061
],
"contour_20_points": [
226.34,
121.76,
147.06,
153.46,
133.04,
158.64,
140.95,
128.25,
146.1,
199.1,
167.13,
140.16,
179.25,
173.74,
148.83,
181.5,
152.82,
166.79,
161.02,
175.55
]
},
"energy_db": {
"p10_p50_p90": [
-84.258,
-16.452,
-7.431
],
"dynamic_range_db": 76.827,
"contour_20_points": [
-61.6,
-30.22,
-36.11,
-13.0,
-8.67,
-4.63,
-7.11,
-20.06,
-84.26,
-84.26,
-25.0,
-7.39,
-10.21,
-6.15,
-84.26,
-24.11,
-21.92,
-84.26,
-7.6,
-48.66
]
},
"timbral_proxies": {
"spectral_centroid_hz_median": 1553.732,
"spectral_flatness_median": 0.014
},
"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": "Ладно. Послушайте. Мы оба наговорили много такого, о чём ещё пожалеем. Но, думаю, наши разногласия можно оставить в прошлом. Ради науки, вы чудовище.",
"text_chars_per_sec": 12.876,
"source": {
"file": "sources_silero/0234.wav",
"sample_rate_for_analysis": 16000,
"duration_sec": 10.6,
"voiced_fraction": 0.702,
"pause_map": [
{
"start": 0.72,
"end": 1.05,
"duration": 0.33
},
{
"start": 1.77,
"end": 2.19,
"duration": 0.42
},
{
"start": 4.9,
"end": 5.27,
"duration": 0.37
},
{
"start": 5.58,
"end": 5.67,
"duration": 0.09
},
{
"start": 6.21,
"end": 6.3,
"duration": 0.09
},
{
"start": 8.37,
"end": 8.76,
"duration": 0.39
},
{
"start": 9.59,
"end": 9.71,
"duration": 0.12
}
],
"f0_hz": {
"median": 200.487,
"p10_p90": [
175.545,
242.589
],
"contour_20_points": [
252.6,
174.38,
243.99,
199.28,
225.25,
200.49,
199.94,
194.72,
189.98,
208.93,
234.47,
211.57,
184.16,
194.25,
175.95,
209.63,
199.76,
192.08,
180.25,
161.91
]
},
"energy_db": {
"p10_p50_p90": [
-63.631,
-24.666,
-16.533
],
"dynamic_range_db": 47.098,
"contour_20_points": [
-74.29,
-23.38,
-15.93,
-32.94,
-15.09,
-18.05,
-20.94,
-25.39,
-22.57,
-77.7,
-45.78,
-23.11,
-27.31,
-19.96,
-33.76,
-45.06,
-17.73,
-25.3,
-20.13,
-85.98
]
},
"timbral_proxies": {
"spectral_centroid_hz_median": 1301.132,
"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": "Ладно. Послушайте. Мы оба наговорили много такого, о чём ещё пожалеем. Но, думаю, наши разногласия можно оставить в прошлом. Ради науки, вы чудовище.",
"text_chars_per_sec": 14.057
},
"pipeline_control": {
"tts_text": "Ладно. Послушайте. Мы оба наговорили много такого, о чём ещё пожалеем. Но, думаю, наши разногласия можно оставить в прошлом. Ради науки, вы чудовище.",
"duration_stage": "pre",
"speaker_reference": "0234"
}
}