deepgeek/silero-vad
2
0
Fork 0
mirror of https://github.com/snakers4/silero-vad.git synced 2026-02-05 18:09:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

fx stram imitation example bug

Browse Source
This commit is contained in:
adamnsandle
2022-04-05 11:33:34 +00:00
parent 6cc08b1077
commit 6e9fd77500
1 changed files with 9 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
silero-vad.ipynb
View File

@@ -134,11 +134,14 @@
"## using VADIterator class\n", "## using VADIterator class\n",
"\n", "\n",
"vad_iterator = VADIterator(model)\n", "vad_iterator = VADIterator(model)\n",
"wav = read_audio(f'en_example.wav', sampling_rate=SAMPLING_RATE)\n", "#wav = read_audio(f'en_example.wav', sampling_rate=SAMPLING_RATE)\n",
"\n", "\n",
"window_size_samples = 1536 # number of samples in a single audio chunk\n", "window_size_samples = 1536 # number of samples in a single audio chunk\n",
"for i in range(0, len(wav), window_size_samples):\n", "for i in range(0, len(wav), window_size_samples):\n",
" speech_dict = vad_iterator(wav[i: i+ window_size_samples], return_seconds=True)\n", " chunk = wav[i: i+ window_size_samples]\n",
" if len(chunk) < window_size_samples:\n",
" break\n",
" speech_dict = vad_iterator(chunk, return_seconds=True)\n",
" if speech_dict:\n", " if speech_dict:\n",
" print(speech_dict, end=' ')\n", " print(speech_dict, end=' ')\n",
"vad_iterator.reset_states() # reset model states after each audio" "vad_iterator.reset_states() # reset model states after each audio"
@@ -158,7 +161,10 @@
"speech_probs = []\n", "speech_probs = []\n",
"window_size_samples = 1536\n", "window_size_samples = 1536\n",
"for i in range(0, len(wav), window_size_samples):\n", "for i in range(0, len(wav), window_size_samples):\n",
" speech_prob = model(wav[i: i+ window_size_samples], SAMPLING_RATE).item()\n", " chunk = wav[i: i+ window_size_samples]\n",
" if len(chunk) < window_size_samples:\n",
" break\n",
" speech_prob = model(chunk, SAMPLING_RATE).item()\n",
" speech_probs.append(speech_prob)\n", " speech_probs.append(speech_prob)\n",
"vad_iterator.reset_states() # reset model states after each audio\n", "vad_iterator.reset_states() # reset model states after each audio\n",
"\n", "\n",