streamer45 / silero-vad-go

A Golang (CGO) implementation of a Silero VAD powered speech detector
MIT License
21 stars 11 forks source link

Discrepant segments from silero-vad-go and the Python package #16

Open wjkoh opened 1 week ago

wjkoh commented 1 week ago

Hi @streamer45, thanks for your awesome package! I found discrepancies between silero-vad-go and the Python package. My input file is a 13-minute-long speech of JFK, and silero-vad-go misses multiple segments that the Python one can detect.

The input file is output.wav.zip.

The following results are from silero-vad-go:

2024/10/20 18:00:25 speech starts at 4.80s
2024/10/20 18:00:25 speech ends at 9.53s
2024/10/20 18:00:25 speech starts at 10.43s
2024/10/20 18:00:25 speech ends at 12.00s
2024/10/20 18:00:25 speech starts at 12.29s
2024/10/20 18:00:25 speech ends at 14.65s
2024/10/20 18:00:25 speech starts at 15.01s
2024/10/20 18:00:25 speech ends at 17.53s
2024/10/20 18:00:25 speech starts at 196.74s
2024/10/20 18:00:25 speech ends at 196.93s
2024/10/20 18:00:25 speech starts at 209.86s
2024/10/20 18:00:25 speech ends at 210.11s
2024/10/20 18:00:25 speech starts at 214.18s
...

The following results are from silero-vad (Python):

[{'start': 4.3, 'end': 9.6}, {'start': 10.1, 'end': 14.6}, {'start': 15.0, 'end': 17.5}, {'start': 18.2, 'end': 18.6}, {'start': 31.8, 'end': 33.4}, {'start': 35.0, 'end': 36.6}, {'start': 37.1, 'end': 39.6}, {'start': 59.7, 'end': 60.3}, {'start': 61.3, 'end': 62.3}, {'start': 64.0, 'end': 64.5}, {'start': 64.8, 'end': 65.4}, {'start': 65.7, 'end': 66.8}, {'start': 67.5, 'end': 69.1}, {'start': 70.4, 'end': 72.1}, {'start': 73.0, 'end': 74.2}, {'start': 74.5, 'end': 76.3}, {'start': 77.1, 'end': 78.0}, {'start': 83.5, 'end': 85.2}, {'start': 86.2, 'end': 87.6}, {'start': 88.4, 'end': 89.8}, {'start': 90.6, 'end': 92.3}, {'start': 92.6, 'end': 94.6}, {'start': 95.1, 'end': 96.0}, {'start': 97.1, 'end': 99.0}, {'start': 99.9, 'end': 101.1}, {'start': 102.0, 'end': 103.4}, {'start': 103.7, 'end': 107.0}, {'start': 107.9, 'end': 108.8}, {'start': 109.2, 'end': 110.9}, {'start': 111.5, 'end': 112.3}, {'start': 112.7, 'end': 113.7}, {'start': 114.9, 'end': 116.7}, {'start': 117.2, 'end': 118.4}, {'start': 119.1, 'end': 121.6}, {'start': 122.0, 'end': 124.0}, {'start': 124.4, 'end': 125.5}, {'start': 135.2, 'end': 136.3}, {'start': 137.6, 'end': 138.6}, {'start': 138.9, 'end': 139.3}, {'start': 140.2, 'end': 140.6}, {'start': 141.1, 'end': 142.4}, {'start': 143.5, 'end': 144.9}, {'start': 145.9, 'end': 146.8}, {'start': 147.7, 'end': 148.6}, {'start': 149.2, 'end': 150.5}, {'start': 152.4, 'end': 153.7}, {'start': 154.8, 'end': 155.9}, {'start': 157.0, 'end': 158.7}, {'start': 158.8, 'end': 160.2}, {'start': 161.0, 'end': 166.2}, {'start': 178.3, 'end': 179.7}, {'start': 181.0, 'end': 182.4}, {'start': 182.8, 'end': 185.2}, {'start': 185.7, 'end': 186.7}, {'start': 187.6, 'end': 189.5}, {'start': 189.7, 'end': 190.1}, {'start': 190.6, 'end': 191.3}, ...

As you can see, silero-vad-go couldn't detect any speech from 17.53s to 196.74s, but silero-vad (Python) found many segments in the time range. I used the .onnx file at https://github.com/snakers4/silero-vad/blob/fd41da0b1544982e7369c3eb4a64c64be58cfef0/src/silero_vad/data/silero_vad.onnx.

streamer45 commented 4 days ago

@wjkoh Weird, this is the output I am getting with using the provided file:

Output 2024/10/23 09:31:18 speech starts at 4.32s 2024/10/23 09:31:18 speech ends at 9.66s 2024/10/23 09:31:18 speech starts at 10.15s 2024/10/23 09:31:18 speech ends at 14.65s 2024/10/23 09:31:18 speech starts at 15.01s 2024/10/23 09:31:18 speech ends at 17.50s 2024/10/23 09:31:18 speech starts at 17.76s 2024/10/23 09:31:18 speech ends at 18.01s 2024/10/23 09:31:18 speech starts at 18.24s 2024/10/23 09:31:18 speech ends at 18.59s 2024/10/23 09:31:18 speech starts at 31.78s 2024/10/23 09:31:18 speech ends at 33.41s 2024/10/23 09:31:18 speech starts at 35.01s 2024/10/23 09:31:18 speech ends at 36.67s 2024/10/23 09:31:18 speech starts at 37.12s 2024/10/23 09:31:18 speech ends at 39.68s 2024/10/23 09:31:18 speech starts at 57.76s 2024/10/23 09:31:18 speech ends at 58.08s 2024/10/23 09:31:18 speech starts at 59.71s 2024/10/23 09:31:18 speech ends at 60.32s 2024/10/23 09:31:18 speech starts at 61.31s 2024/10/23 09:31:18 speech ends at 62.33s 2024/10/23 09:31:18 speech starts at 64.03s 2024/10/23 09:31:18 speech ends at 64.57s 2024/10/23 09:31:18 speech starts at 64.83s 2024/10/23 09:31:18 speech ends at 65.44s 2024/10/23 09:31:18 speech starts at 65.73s 2024/10/23 09:31:18 speech ends at 66.78s 2024/10/23 09:31:18 speech starts at 67.46s 2024/10/23 09:31:18 speech ends at 69.12s 2024/10/23 09:31:18 speech starts at 70.37s 2024/10/23 09:31:18 speech ends at 72.16s 2024/10/23 09:31:18 speech starts at 72.96s 2024/10/23 09:31:18 speech ends at 74.24s 2024/10/23 09:31:18 speech starts at 74.50s 2024/10/23 09:31:18 speech ends at 76.35s 2024/10/23 09:31:18 speech starts at 77.09s 2024/10/23 09:31:18 speech ends at 78.01s 2024/10/23 09:31:18 speech starts at 83.46s 2024/10/23 09:31:18 speech ends at 85.21s 2024/10/23 09:31:18 speech starts at 86.24s 2024/10/23 09:31:18 speech ends at 87.61s 2024/10/23 09:31:18 speech starts at 88.35s 2024/10/23 09:31:18 speech ends at 89.79s 2024/10/23 09:31:18 speech starts at 90.63s 2024/10/23 09:31:18 speech ends at 92.29s 2024/10/23 09:31:18 speech starts at 92.64s 2024/10/23 09:31:18 speech ends at 94.65s 2024/10/23 09:31:18 speech starts at 95.11s 2024/10/23 09:31:18 speech ends at 96.00s 2024/10/23 09:31:18 speech starts at 97.12s 2024/10/23 09:31:18 speech ends at 99.07s 2024/10/23 09:31:18 speech starts at 99.87s 2024/10/23 09:31:18 speech ends at 101.12s 2024/10/23 09:31:18 speech starts at 101.95s 2024/10/23 09:31:18 speech ends at 103.45s 2024/10/23 09:31:18 speech starts at 103.71s 2024/10/23 09:31:18 speech ends at 107.04s 2024/10/23 09:31:18 speech starts at 107.91s 2024/10/23 09:31:18 speech ends at 108.86s 2024/10/23 09:31:18 speech starts at 109.22s 2024/10/23 09:31:18 speech ends at 110.94s 2024/10/23 09:31:18 speech starts at 111.49s 2024/10/23 09:31:18 speech ends at 112.35s 2024/10/23 09:31:18 speech starts at 112.67s 2024/10/23 09:31:18 speech ends at 113.76s 2024/10/23 09:31:18 speech starts at 114.91s 2024/10/23 09:31:18 speech ends at 116.70s 2024/10/23 09:31:18 speech starts at 117.25s 2024/10/23 09:31:18 speech ends at 118.40s 2024/10/23 09:31:18 speech starts at 119.07s 2024/10/23 09:31:18 speech ends at 121.60s 2024/10/23 09:31:18 speech starts at 122.02s 2024/10/23 09:31:18 speech ends at 124.06s 2024/10/23 09:31:18 speech starts at 124.35s 2024/10/23 09:31:18 speech ends at 125.50s 2024/10/23 09:31:18 speech starts at 135.20s 2024/10/23 09:31:18 speech ends at 136.29s 2024/10/23 09:31:18 speech starts at 137.63s 2024/10/23 09:31:18 speech ends at 138.59s 2024/10/23 09:31:18 speech starts at 138.91s 2024/10/23 09:31:18 speech ends at 139.36s 2024/10/23 09:31:18 speech starts at 140.16s 2024/10/23 09:31:18 speech ends at 140.64s 2024/10/23 09:31:18 speech starts at 141.06s 2024/10/23 09:31:18 speech ends at 142.40s 2024/10/23 09:31:18 speech starts at 143.49s 2024/10/23 09:31:18 speech ends at 144.93s 2024/10/23 09:31:18 speech starts at 145.67s 2024/10/23 09:31:18 speech ends at 145.79s 2024/10/23 09:31:18 speech starts at 145.86s 2024/10/23 09:31:18 speech ends at 146.81s 2024/10/23 09:31:18 speech starts at 147.68s 2024/10/23 09:31:18 speech ends at 148.64s 2024/10/23 09:31:18 speech starts at 149.25s 2024/10/23 09:31:18 speech ends at 150.56s 2024/10/23 09:31:18 speech starts at 152.39s 2024/10/23 09:31:18 speech ends at 153.76s 2024/10/23 09:31:18 speech starts at 154.85s 2024/10/23 09:31:18 speech ends at 155.90s 2024/10/23 09:31:18 speech starts at 156.96s 2024/10/23 09:31:18 speech ends at 158.72s 2024/10/23 09:31:18 speech starts at 158.79s 2024/10/23 09:31:18 speech ends at 160.19s 2024/10/23 09:31:18 speech starts at 160.99s 2024/10/23 09:31:18 speech ends at 166.27s 2024/10/23 09:31:18 speech starts at 178.27s 2024/10/23 09:31:18 speech ends at 179.74s 2024/10/23 09:31:18 speech starts at 181.03s 2024/10/23 09:31:18 speech ends at 182.43s 2024/10/23 09:31:18 speech starts at 182.85s 2024/10/23 09:31:18 speech ends at 185.21s 2024/10/23 09:31:18 speech starts at 185.70s 2024/10/23 09:31:18 speech ends at 186.75s 2024/10/23 09:31:18 speech starts at 187.59s 2024/10/23 09:31:18 speech ends at 189.53s 2024/10/23 09:31:18 speech starts at 189.67s 2024/10/23 09:31:18 speech ends at 190.14s 2024/10/23 09:31:18 speech starts at 190.56s 2024/10/23 09:31:18 speech ends at 191.36s 2024/10/23 09:31:18 speech starts at 192.39s 2024/10/23 09:31:18 speech ends at 194.97s 2024/10/23 09:31:18 speech starts at 195.94s 2024/10/23 09:31:18 speech ends at 197.76s 2024/10/23 09:31:18 speech starts at 198.95s 2024/10/23 09:31:18 speech ends at 201.57s 2024/10/23 09:31:18 speech starts at 201.95s 2024/10/23 09:31:18 speech ends at 203.17s 2024/10/23 09:31:18 speech starts at 203.43s 2024/10/23 09:31:18 speech ends at 206.46s 2024/10/23 09:31:18 speech starts at 207.20s 2024/10/23 09:31:18 speech ends at 210.21s 2024/10/23 09:31:18 speech starts at 210.27s 2024/10/23 09:31:18 speech ends at 211.29s 2024/10/23 09:31:18 speech starts at 211.87s 2024/10/23 09:31:18 speech ends at 213.37s 2024/10/23 09:31:18 speech starts at 213.89s 2024/10/23 09:31:18 speech ends at 215.52s 2024/10/23 09:31:18 speech starts at 215.97s 2024/10/23 09:31:18 speech ends at 218.65s 2024/10/23 09:31:18 speech starts at 219.30s 2024/10/23 09:31:18 speech ends at 221.44s 2024/10/23 09:31:18 speech starts at 221.54s 2024/10/23 09:31:18 speech ends at 222.24s 2024/10/23 09:31:18 speech starts at 222.88s 2024/10/23 09:31:18 speech ends at 223.81s 2024/10/23 09:31:18 speech starts at 223.91s 2024/10/23 09:31:18 speech ends at 225.09s 2024/10/23 09:31:18 speech starts at 225.63s 2024/10/23 09:31:18 speech ends at 228.19s 2024/10/23 09:31:18 speech starts at 228.90s 2024/10/23 09:31:18 speech ends at 231.20s 2024/10/23 09:31:18 speech starts at 231.75s 2024/10/23 09:31:18 speech ends at 233.92s 2024/10/23 09:31:18 speech starts at 234.15s 2024/10/23 09:31:18 speech ends at 235.39s 2024/10/23 09:31:18 speech starts at 235.81s 2024/10/23 09:31:18 speech ends at 236.80s 2024/10/23 09:31:18 speech starts at 237.47s 2024/10/23 09:31:18 speech ends at 240.57s 2024/10/23 09:31:18 speech starts at 241.06s 2024/10/23 09:31:18 speech ends at 242.40s 2024/10/23 09:31:18 speech starts at 242.88s 2024/10/23 09:31:18 speech ends at 245.21s 2024/10/23 09:31:18 speech starts at 245.76s 2024/10/23 09:31:18 speech ends at 247.55s 2024/10/23 09:31:18 speech starts at 248.07s 2024/10/23 09:31:18 speech ends at 250.27s 2024/10/23 09:31:18 speech starts at 250.53s 2024/10/23 09:31:18 speech ends at 252.93s 2024/10/23 09:31:18 speech starts at 253.09s 2024/10/23 09:31:18 speech ends at 254.97s 2024/10/23 09:31:18 speech starts at 255.59s 2024/10/23 09:31:18 speech ends at 257.76s 2024/10/23 09:31:18 speech starts at 257.89s 2024/10/23 09:31:18 speech ends at 258.65s 2024/10/23 09:31:18 speech starts at 259.17s 2024/10/23 09:31:18 speech ends at 260.54s 2024/10/23 09:31:18 speech starts at 270.21s 2024/10/23 09:31:18 speech ends at 272.35s 2024/10/23 09:31:18 speech starts at 272.51s 2024/10/23 09:31:18 speech ends at 273.92s 2024/10/23 09:31:18 speech starts at 274.75s 2024/10/23 09:31:18 speech ends at 275.07s 2024/10/23 09:31:18 speech starts at 275.17s 2024/10/23 09:31:18 speech ends at 275.90s 2024/10/23 09:31:18 speech starts at 276.67s 2024/10/23 09:31:18 speech ends at 280.00s 2024/10/23 09:31:18 speech starts at 280.83s 2024/10/23 09:31:18 speech ends at 284.45s 2024/10/23 09:31:18 speech starts at 285.70s 2024/10/23 09:31:18 speech ends at 286.65s 2024/10/23 09:31:18 speech starts at 286.88s 2024/10/23 09:31:18 speech ends at 288.45s 2024/10/23 09:31:18 speech starts at 289.09s 2024/10/23 09:31:18 speech ends at 289.76s 2024/10/23 09:31:18 speech starts at 290.02s 2024/10/23 09:31:18 speech ends at 291.04s 2024/10/23 09:31:18 speech starts at 291.81s 2024/10/23 09:31:18 speech ends at 292.32s 2024/10/23 09:31:18 speech starts at 293.03s 2024/10/23 09:31:18 speech ends at 294.75s 2024/10/23 09:31:18 speech starts at 295.33s 2024/10/23 09:31:18 speech ends at 297.15s 2024/10/23 09:31:18 speech starts at 297.47s 2024/10/23 09:31:18 speech ends at 298.46s 2024/10/23 09:31:18 speech starts at 299.01s 2024/10/23 09:31:18 speech ends at 300.35s 2024/10/23 09:31:18 speech starts at 300.71s 2024/10/23 09:31:18 speech ends at 301.28s 2024/10/23 09:31:18 speech starts at 301.63s 2024/10/23 09:31:18 speech ends at 302.65s 2024/10/23 09:31:18 speech starts at 303.39s 2024/10/23 09:31:18 speech ends at 304.35s 2024/10/23 09:31:18 speech starts at 304.58s 2024/10/23 09:31:18 speech ends at 305.41s 2024/10/23 09:31:18 speech starts at 306.11s 2024/10/23 09:31:18 speech ends at 306.78s 2024/10/23 09:31:18 speech starts at 307.43s 2024/10/23 09:31:18 speech ends at 308.03s 2024/10/23 09:31:18 speech starts at 308.10s 2024/10/23 09:31:18 speech ends at 309.76s 2024/10/23 09:31:18 speech starts at 309.92s 2024/10/23 09:31:18 speech ends at 311.23s 2024/10/23 09:31:18 speech starts at 311.87s 2024/10/23 09:31:18 speech ends at 315.10s 2024/10/23 09:31:18 speech starts at 315.87s 2024/10/23 09:31:18 speech ends at 320.73s 2024/10/23 09:31:18 speech starts at 320.90s 2024/10/23 09:31:18 speech ends at 321.66s 2024/10/23 09:31:18 speech starts at 322.31s 2024/10/23 09:31:18 speech ends at 323.65s 2024/10/23 09:31:18 speech starts at 323.87s 2024/10/23 09:31:18 speech ends at 325.34s 2024/10/23 09:31:18 speech starts at 325.92s 2024/10/23 09:31:18 speech ends at 326.88s 2024/10/23 09:31:18 speech starts at 326.98s 2024/10/23 09:31:18 speech ends at 327.97s 2024/10/23 09:31:18 speech starts at 328.48s 2024/10/23 09:31:18 speech ends at 329.69s 2024/10/23 09:31:18 speech starts at 330.40s 2024/10/23 09:31:18 speech ends at 332.45s 2024/10/23 09:31:18 speech starts at 333.03s 2024/10/23 09:31:18 speech ends at 335.42s 2024/10/23 09:31:18 speech starts at 335.52s 2024/10/23 09:31:18 speech ends at 337.53s 2024/10/23 09:31:18 speech starts at 338.37s 2024/10/23 09:31:18 speech ends at 340.00s 2024/10/23 09:31:18 speech starts at 340.10s 2024/10/23 09:31:18 speech ends at 341.37s 2024/10/23 09:31:18 speech starts at 341.73s 2024/10/23 09:31:18 speech ends at 342.69s 2024/10/23 09:31:18 speech starts at 343.07s 2024/10/23 09:31:18 speech ends at 344.00s 2024/10/23 09:31:18 speech starts at 344.45s 2024/10/23 09:31:18 speech ends at 346.40s 2024/10/23 09:31:18 speech starts at 347.07s 2024/10/23 09:31:18 speech ends at 350.62s 2024/10/23 09:31:18 speech starts at 350.91s 2024/10/23 09:31:18 speech ends at 352.70s 2024/10/23 09:31:18 speech starts at 353.12s 2024/10/23 09:31:18 speech ends at 355.10s 2024/10/23 09:31:18 speech starts at 355.49s 2024/10/23 09:31:18 speech ends at 357.47s 2024/10/23 09:31:18 speech starts at 357.83s 2024/10/23 09:31:18 speech ends at 360.48s 2024/10/23 09:31:18 speech starts at 361.09s 2024/10/23 09:31:18 speech ends at 363.52s 2024/10/23 09:31:18 speech starts at 373.22s 2024/10/23 09:31:18 speech ends at 374.40s 2024/10/23 09:31:18 speech starts at 375.39s 2024/10/23 09:31:18 speech ends at 376.38s 2024/10/23 09:31:18 speech starts at 376.51s 2024/10/23 09:31:18 speech ends at 377.37s 2024/10/23 09:31:18 speech starts at 377.79s 2024/10/23 09:31:18 speech ends at 379.45s 2024/10/23 09:31:18 speech starts at 380.03s 2024/10/23 09:31:18 speech ends at 381.95s 2024/10/23 09:31:18 speech starts at 382.40s 2024/10/23 09:31:18 speech ends at 384.13s 2024/10/23 09:31:18 speech starts at 384.83s 2024/10/23 09:31:18 speech ends at 386.62s 2024/10/23 09:31:18 speech starts at 386.79s 2024/10/23 09:31:18 speech ends at 387.71s 2024/10/23 09:31:18 speech starts at 387.78s 2024/10/23 09:31:18 speech ends at 388.86s 2024/10/23 09:31:18 speech starts at 389.15s 2024/10/23 09:31:18 speech ends at 390.81s 2024/10/23 09:31:18 speech starts at 391.30s 2024/10/23 09:31:18 speech ends at 392.86s 2024/10/23 09:31:18 speech starts at 393.15s 2024/10/23 09:31:18 speech ends at 396.51s 2024/10/23 09:31:18 speech starts at 397.09s 2024/10/23 09:31:18 speech ends at 398.81s 2024/10/23 09:31:18 speech starts at 399.49s 2024/10/23 09:31:18 speech ends at 401.18s 2024/10/23 09:31:18 speech starts at 401.60s 2024/10/23 09:31:18 speech ends at 403.10s 2024/10/23 09:31:18 speech starts at 403.91s 2024/10/23 09:31:18 speech ends at 408.32s 2024/10/23 09:31:18 speech starts at 408.42s 2024/10/23 09:31:18 speech ends at 409.44s 2024/10/23 09:31:18 speech starts at 409.92s 2024/10/23 09:31:18 speech ends at 411.61s 2024/10/23 09:31:18 speech starts at 412.19s 2024/10/23 09:31:18 speech ends at 414.56s 2024/10/23 09:31:18 speech starts at 415.14s 2024/10/23 09:31:18 speech ends at 417.79s 2024/10/23 09:31:18 speech starts at 418.08s 2024/10/23 09:31:18 speech ends at 421.44s 2024/10/23 09:31:18 speech starts at 421.57s 2024/10/23 09:31:18 speech ends at 422.24s 2024/10/23 09:31:18 speech starts at 422.88s 2024/10/23 09:31:18 speech ends at 424.38s 2024/10/23 09:31:18 speech starts at 424.51s 2024/10/23 09:31:18 speech ends at 426.97s 2024/10/23 09:31:18 speech starts at 427.81s 2024/10/23 09:31:18 speech ends at 428.93s 2024/10/23 09:31:18 speech starts at 429.06s 2024/10/23 09:31:18 speech ends at 430.08s 2024/10/23 09:31:18 speech starts at 431.78s 2024/10/23 09:31:18 speech ends at 432.77s 2024/10/23 09:31:18 speech starts at 433.89s 2024/10/23 09:31:18 speech ends at 435.33s 2024/10/23 09:31:18 speech starts at 436.39s 2024/10/23 09:31:18 speech ends at 436.86s 2024/10/23 09:31:18 speech starts at 437.60s 2024/10/23 09:31:18 speech ends at 440.48s 2024/10/23 09:31:18 speech starts at 441.03s 2024/10/23 09:31:18 speech ends at 442.81s 2024/10/23 09:31:18 speech starts at 443.68s 2024/10/23 09:31:18 speech ends at 446.40s 2024/10/23 09:31:18 speech starts at 446.91s 2024/10/23 09:31:18 speech ends at 448.99s 2024/10/23 09:31:18 speech starts at 449.44s 2024/10/23 09:31:18 speech ends at 449.82s 2024/10/23 09:31:18 speech starts at 449.89s 2024/10/23 09:31:18 speech ends at 450.56s 2024/10/23 09:31:18 speech starts at 450.69s 2024/10/23 09:31:18 speech ends at 452.35s 2024/10/23 09:31:18 speech starts at 453.12s 2024/10/23 09:31:18 speech ends at 453.76s 2024/10/23 09:31:18 speech starts at 453.89s 2024/10/23 09:31:18 speech ends at 455.49s 2024/10/23 09:31:18 speech starts at 456.16s 2024/10/23 09:31:18 speech ends at 459.07s 2024/10/23 09:31:18 speech starts at 459.36s 2024/10/23 09:31:18 speech ends at 460.77s 2024/10/23 09:31:18 speech starts at 461.63s 2024/10/23 09:31:18 speech ends at 465.21s 2024/10/23 09:31:18 speech starts at 466.08s 2024/10/23 09:31:18 speech ends at 466.85s 2024/10/23 09:31:18 speech starts at 467.14s 2024/10/23 09:31:18 speech ends at 468.38s 2024/10/23 09:31:18 speech starts at 469.03s 2024/10/23 09:31:18 speech ends at 471.42s 2024/10/23 09:31:18 speech starts at 471.91s 2024/10/23 09:31:18 speech ends at 474.94s 2024/10/23 09:31:18 speech starts at 475.75s 2024/10/23 09:31:18 speech ends at 477.25s 2024/10/23 09:31:18 speech starts at 477.63s 2024/10/23 09:31:18 speech ends at 480.35s 2024/10/23 09:31:18 speech starts at 480.64s 2024/10/23 09:31:18 speech ends at 485.02s 2024/10/23 09:31:18 speech starts at 485.51s 2024/10/23 09:31:18 speech ends at 486.65s 2024/10/23 09:31:18 speech starts at 487.33s 2024/10/23 09:31:18 speech ends at 489.98s 2024/10/23 09:31:18 speech starts at 490.31s 2024/10/23 09:31:18 speech ends at 492.22s 2024/10/23 09:31:18 speech starts at 492.71s 2024/10/23 09:31:18 speech ends at 496.06s 2024/10/23 09:31:18 speech starts at 496.39s 2024/10/23 09:31:18 speech ends at 497.69s 2024/10/23 09:31:18 speech starts at 498.08s 2024/10/23 09:31:18 speech ends at 499.10s 2024/10/23 09:31:18 speech starts at 499.62s 2024/10/23 09:31:18 speech ends at 502.40s 2024/10/23 09:31:18 speech starts at 502.69s 2024/10/23 09:31:18 speech ends at 503.81s 2024/10/23 09:31:18 speech starts at 504.35s 2024/10/23 09:31:18 speech ends at 505.82s 2024/10/23 09:31:18 speech starts at 506.31s 2024/10/23 09:31:18 speech ends at 508.19s 2024/10/23 09:31:18 speech starts at 508.71s 2024/10/23 09:31:18 speech ends at 510.81s 2024/10/23 09:31:18 speech starts at 519.36s 2024/10/23 09:31:18 speech ends at 521.31s 2024/10/23 09:31:18 speech starts at 521.67s 2024/10/23 09:31:18 speech ends at 522.88s 2024/10/23 09:31:18 speech starts at 523.65s 2024/10/23 09:31:18 speech ends at 526.81s 2024/10/23 09:31:18 speech starts at 527.52s 2024/10/23 09:31:18 speech ends at 531.42s 2024/10/23 09:31:18 speech starts at 532.16s 2024/10/23 09:31:18 speech ends at 535.93s 2024/10/23 09:31:18 speech starts at 536.32s 2024/10/23 09:31:18 speech ends at 537.50s 2024/10/23 09:31:18 speech starts at 537.60s 2024/10/23 09:31:18 speech ends at 538.56s 2024/10/23 09:31:18 speech starts at 538.85s 2024/10/23 09:31:18 speech ends at 543.04s 2024/10/23 09:31:18 speech starts at 548.55s 2024/10/23 09:31:18 speech ends at 550.14s 2024/10/23 09:31:18 speech starts at 551.30s 2024/10/23 09:31:18 speech ends at 552.29s 2024/10/23 09:31:18 speech starts at 552.39s 2024/10/23 09:31:18 speech ends at 553.25s 2024/10/23 09:31:18 speech starts at 553.41s 2024/10/23 09:31:18 speech ends at 554.65s 2024/10/23 09:31:18 speech starts at 555.20s 2024/10/23 09:31:18 speech ends at 558.72s 2024/10/23 09:31:18 speech starts at 559.39s 2024/10/23 09:31:18 speech ends at 561.53s 2024/10/23 09:31:18 speech starts at 561.95s 2024/10/23 09:31:18 speech ends at 562.72s 2024/10/23 09:31:18 speech starts at 563.33s 2024/10/23 09:31:18 speech ends at 564.86s 2024/10/23 09:31:18 speech starts at 565.35s 2024/10/23 09:31:18 speech ends at 567.29s 2024/10/23 09:31:18 speech starts at 567.43s 2024/10/23 09:31:18 speech ends at 568.32s 2024/10/23 09:31:18 speech starts at 568.90s 2024/10/23 09:31:18 speech ends at 572.00s 2024/10/23 09:31:18 speech starts at 572.51s 2024/10/23 09:31:18 speech ends at 575.55s 2024/10/23 09:31:18 speech starts at 576.71s 2024/10/23 09:31:18 speech ends at 578.81s 2024/10/23 09:31:18 speech starts at 579.43s 2024/10/23 09:31:18 speech ends at 581.21s 2024/10/23 09:31:18 speech starts at 581.60s 2024/10/23 09:31:18 speech ends at 584.61s 2024/10/23 09:31:18 speech starts at 585.28s 2024/10/23 09:31:18 speech ends at 586.37s 2024/10/23 09:31:18 speech starts at 587.27s 2024/10/23 09:31:18 speech ends at 589.34s 2024/10/23 09:31:18 speech starts at 590.56s 2024/10/23 09:31:18 speech ends at 593.05s 2024/10/23 09:31:18 speech starts at 593.57s 2024/10/23 09:31:18 speech ends at 598.08s 2024/10/23 09:31:18 speech starts at 598.50s 2024/10/23 09:31:18 speech ends at 601.92s 2024/10/23 09:31:18 speech starts at 602.11s 2024/10/23 09:31:18 speech ends at 604.93s 2024/10/23 09:31:18 speech starts at 605.35s 2024/10/23 09:31:18 speech ends at 606.94s 2024/10/23 09:31:18 speech starts at 607.52s 2024/10/23 09:31:18 speech ends at 609.25s 2024/10/23 09:31:18 speech starts at 609.79s 2024/10/23 09:31:18 speech ends at 611.58s 2024/10/23 09:31:18 speech starts at 612.16s 2024/10/23 09:31:18 speech ends at 615.23s 2024/10/23 09:31:18 speech starts at 615.62s 2024/10/23 09:31:18 speech ends at 616.41s 2024/10/23 09:31:18 speech starts at 616.71s 2024/10/23 09:31:18 speech ends at 621.09s 2024/10/23 09:31:18 speech starts at 629.15s 2024/10/23 09:31:18 speech ends at 630.56s 2024/10/23 09:31:18 speech starts at 631.49s 2024/10/23 09:31:18 speech ends at 632.57s 2024/10/23 09:31:18 speech starts at 633.22s 2024/10/23 09:31:18 speech ends at 635.97s 2024/10/23 09:31:18 speech starts at 636.74s 2024/10/23 09:31:18 speech ends at 637.12s 2024/10/23 09:31:18 speech starts at 637.19s 2024/10/23 09:31:18 speech ends at 637.95s 2024/10/23 09:31:18 speech starts at 638.75s 2024/10/23 09:31:18 speech ends at 642.33s 2024/10/23 09:31:18 speech starts at 642.98s 2024/10/23 09:31:18 speech ends at 644.06s 2024/10/23 09:31:18 speech starts at 644.39s 2024/10/23 09:31:18 speech ends at 645.53s 2024/10/23 09:31:18 speech starts at 646.31s 2024/10/23 09:31:18 speech ends at 649.47s 2024/10/23 09:31:18 speech starts at 650.18s 2024/10/23 09:31:18 speech ends at 653.85s 2024/10/23 09:31:18 speech starts at 654.18s 2024/10/23 09:31:18 speech ends at 656.73s 2024/10/23 09:31:18 speech starts at 657.41s 2024/10/23 09:31:18 speech ends at 660.57s 2024/10/23 09:31:18 speech starts at 661.22s 2024/10/23 09:31:18 speech ends at 662.24s 2024/10/23 09:31:18 speech starts at 662.31s 2024/10/23 09:31:18 speech ends at 664.06s 2024/10/23 09:31:18 speech starts at 664.39s 2024/10/23 09:31:18 speech ends at 667.04s 2024/10/23 09:31:18 speech starts at 667.52s 2024/10/23 09:31:18 speech ends at 668.83s 2024/10/23 09:31:18 speech starts at 669.19s 2024/10/23 09:31:18 speech ends at 671.61s 2024/10/23 09:31:18 speech starts at 671.94s 2024/10/23 09:31:18 speech ends at 673.47s 2024/10/23 09:31:18 speech starts at 673.89s 2024/10/23 09:31:18 speech ends at 677.12s 2024/10/23 09:31:18 speech starts at 677.51s 2024/10/23 09:31:18 speech ends at 678.72s 2024/10/23 09:31:18 speech starts at 679.39s 2024/10/23 09:31:18 speech ends at 680.86s 2024/10/23 09:31:18 speech starts at 680.99s 2024/10/23 09:31:18 speech ends at 681.95s 2024/10/23 09:31:18 speech starts at 682.98s 2024/10/23 09:31:18 speech ends at 684.38s 2024/10/23 09:31:18 speech starts at 684.77s 2024/10/23 09:31:18 speech ends at 687.58s 2024/10/23 09:31:18 speech starts at 688.00s 2024/10/23 09:31:18 speech ends at 688.57s 2024/10/23 09:31:18 speech starts at 689.47s 2024/10/23 09:31:18 speech ends at 692.06s 2024/10/23 09:31:18 speech starts at 692.83s 2024/10/23 09:31:18 speech ends at 695.55s 2024/10/23 09:31:18 speech starts at 695.81s 2024/10/23 09:31:18 speech ends at 696.73s 2024/10/23 09:31:18 speech starts at 696.96s 2024/10/23 09:31:18 speech ends at 697.82s 2024/10/23 09:31:18 speech starts at 697.92s 2024/10/23 09:31:18 speech ends at 699.45s 2024/10/23 09:31:18 speech starts at 700.03s 2024/10/23 09:31:18 speech ends at 702.27s 2024/10/23 09:31:18 speech starts at 702.59s 2024/10/23 09:31:18 speech ends at 705.18s 2024/10/23 09:31:18 speech starts at 705.83s 2024/10/23 09:31:18 speech ends at 711.87s 2024/10/23 09:31:18 speech starts at 712.42s 2024/10/23 09:31:18 speech ends at 714.01s 2024/10/23 09:31:18 speech starts at 714.47s 2024/10/23 09:31:18 speech ends at 715.55s 2024/10/23 09:31:18 speech starts at 715.68s 2024/10/23 09:31:18 speech ends at 716.89s 2024/10/23 09:31:18 speech starts at 717.09s 2024/10/23 09:31:18 speech ends at 718.40s 2024/10/23 09:31:18 speech starts at 718.50s 2024/10/23 09:31:18 speech ends at 719.68s 2024/10/23 09:31:18 speech starts at 720.19s 2024/10/23 09:31:18 speech ends at 721.12s 2024/10/23 09:31:18 speech starts at 721.31s 2024/10/23 09:31:18 speech ends at 722.37s 2024/10/23 09:31:18 speech starts at 722.85s 2024/10/23 09:31:18 speech ends at 724.70s 2024/10/23 09:31:18 speech starts at 725.19s 2024/10/23 09:31:18 speech ends at 727.90s 2024/10/23 09:31:18 speech starts at 732.96s 2024/10/23 09:31:18 speech ends at 735.39s 2024/10/23 09:31:18 speech starts at 735.75s 2024/10/23 09:31:18 speech ends at 738.30s 2024/10/23 09:31:18 speech starts at 738.91s 2024/10/23 09:31:18 speech ends at 740.70s 2024/10/23 09:31:18 speech starts at 741.28s 2024/10/23 09:31:18 speech ends at 742.37s 2024/10/23 09:31:18 speech starts at 742.79s 2024/10/23 09:31:18 speech ends at 744.93s 2024/10/23 09:31:18 speech starts at 745.19s 2024/10/23 09:31:18 speech ends at 746.21s 2024/10/23 09:31:18 speech starts at 746.91s 2024/10/23 09:31:18 speech ends at 748.35s 2024/10/23 09:31:18 speech starts at 748.48s 2024/10/23 09:31:18 speech ends at 749.28s 2024/10/23 09:31:18 speech starts at 749.95s 2024/10/23 09:31:18 speech ends at 751.71s 2024/10/23 09:31:18 speech starts at 752.07s 2024/10/23 09:31:18 speech ends at 752.96s 2024/10/23 09:31:18 speech starts at 753.25s 2024/10/23 09:31:18 speech ends at 754.53s 2024/10/23 09:31:18 speech starts at 755.17s 2024/10/23 09:31:18 speech ends at 756.32s 2024/10/23 09:31:18 speech starts at 756.93s 2024/10/23 09:31:18 speech ends at 757.31s 2024/10/23 09:31:18 speech starts at 757.70s 2024/10/23 09:31:18 speech ends at 759.10s 2024/10/23 09:31:18 speech starts at 759.49s 2024/10/23 09:31:18 speech ends at 761.28s 2024/10/23 09:31:18 speech starts at 761.51s 2024/10/23 09:31:18 speech ends at 762.81s 2024/10/23 09:31:18 speech starts at 763.52s 2024/10/23 09:31:18 speech ends at 766.05s 2024/10/23 09:31:18 speech starts at 766.11s 2024/10/23 09:31:18 speech ends at 767.13s 2024/10/23 09:31:18 speech starts at 767.65s 2024/10/23 09:31:18 speech ends at 769.21s 2024/10/23 09:31:18 speech starts at 769.89s 2024/10/23 09:31:18 speech ends at 774.30s 2024/10/23 09:31:18 speech starts at 774.88s 2024/10/23 09:31:18 speech ends at 776.86s 2024/10/23 09:31:18 speech starts at 776.99s 2024/10/23 09:31:18 speech ends at 778.08s 2024/10/23 09:31:18 speech starts at 778.63s 2024/10/23 09:31:18 speech ends at 779.81s 2024/10/23 09:31:18 speech starts at 780.35s 2024/10/23 09:31:18 speech ends at 782.49s 2024/10/23 09:31:18 speech starts at 782.79s 2024/10/23 09:31:18 speech ends at 784.00s 2024/10/23 09:31:18 speech starts at 784.55s 2024/10/23 09:31:18 speech ends at 786.65s 2024/10/23 09:31:18 speech starts at 787.07s 2024/10/23 09:31:18 speech ends at 788.29s 2024/10/23 09:31:18 speech starts at 788.67s 2024/10/23 09:31:18 speech ends at 788.86s 2024/10/23 09:31:18 speech starts at 788.96s 2024/10/23 09:31:18 speech ends at 789.47s 2024/10/23 09:31:18 speech starts at 789.73s 2024/10/23 09:31:18 speech ends at 790.97s 2024/10/23 09:31:18 speech starts at 791.36s 2024/10/23 09:31:18 speech ends at 791.58s

Silero model is the same. Using onnxruntime-linux-x64-1.18.1.