From 6e9fd775009490397d12b98a7263bead0fc04cca Mon Sep 17 00:00:00 2001 From: adamnsandle Date: Tue, 5 Apr 2022 11:33:34 +0000 Subject: [PATCH 1/2] fx stram imitation example bug --- silero-vad.ipynb | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/silero-vad.ipynb b/silero-vad.ipynb index f2d3fa2..1a5560d 100644 --- a/silero-vad.ipynb +++ b/silero-vad.ipynb @@ -134,11 +134,14 @@ "## using VADIterator class\n", "\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", "window_size_samples = 1536 # number of samples in a single audio chunk\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", " print(speech_dict, end=' ')\n", "vad_iterator.reset_states() # reset model states after each audio" @@ -158,7 +161,10 @@ "speech_probs = []\n", "window_size_samples = 1536\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", "vad_iterator.reset_states() # reset model states after each audio\n", "\n", From 8cdc8d36c98ad96627f352b226711b819c60968f Mon Sep 17 00:00:00 2001 From: adamnsandle Date: Tue, 5 Apr 2022 11:35:23 +0000 Subject: [PATCH 2/2] fx --- silero-vad.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/silero-vad.ipynb b/silero-vad.ipynb index 1a5560d..d9c62e8 100644 --- a/silero-vad.ipynb +++ b/silero-vad.ipynb @@ -134,7 +134,7 @@ "## using VADIterator class\n", "\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", "window_size_samples = 1536 # number of samples in a single audio chunk\n", "for i in range(0, len(wav), window_size_samples):\n",