fix snakers4 silero-vad utils expansion (pytorch#261)

* fix utils expansion * get_speech_timestamp => get_speech_ts * get_speech_timestamps sampling rate * Update snakers4_silero-vad_vad.md Co-authored-by: Nicolas Hug <[email protected]> * Update snakers4_silero-vad_vad.md Co-authored-by: Nicolas Hug <[email protected]> Co-authored-by: Nicolas Hug <[email protected]>
zjhzjh111 · Dec 14, 2021 · 3bdedd9 · 3bdedd9
1 parent 94f0352
commit 3bdedd9
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 8 deletions.
diff --git a/snakers4_silero-vad_language.md b/snakers4_silero-vad_language.md
@@ -31,7 +31,7 @@ model, utils = torch.hub.load(repo_or_dir='snakers4/silero-vad',
                               model='silero_lang_detector',
                               force_reload=True)
 
-get_language, read_audio = utils
+get_language, read_audio, *_ = utils
 
 files_dir = torch.hub.get_dir() + '/snakers4_silero-vad_master/files'
 

diff --git a/snakers4_silero-vad_number.md b/snakers4_silero-vad_number.md
@@ -32,7 +32,7 @@ model, utils = torch.hub.load(repo_or_dir='snakers4/silero-vad',
 
 (get_number_ts,
  _, read_audio,
- _, _) = utils
+ *_) = utils
 
 files_dir = torch.hub.get_dir() + '/snakers4_silero-vad_master/files'
 

diff --git a/snakers4_silero-vad_vad.md b/snakers4_silero-vad_vad.md
@@ -24,22 +24,24 @@ pip install -q torchaudio soundfile
 
 ```python
 import torch
+
 torch.set_num_threads(1)
 from pprint import pprint
 
 model, utils = torch.hub.load(repo_or_dir='snakers4/silero-vad',
                               model='silero_vad',
                               force_reload=True)
 
-(get_speech_ts,
- _, _, read_audio,
- _, _, _) = utils
+(get_speech_timestamps,
+ _, read_audio,
+ *_) = utils
 
 files_dir = torch.hub.get_dir() + '/snakers4_silero-vad_master/files'
 
-wav = read_audio(f'{files_dir}/en.wav')
-speech_timestamps = get_speech_ts(wav, model,
-                                  num_steps=4)
+sampling_rate = 16000  # also accepts 8000
+wav = read_audio(f'{files_dir}/en.wav', sampling_rate=sampling_rate)
+speech_timestamps = get_speech_timestamps(wav, model, sampling_rate=sampling_rate)  # see docstring for other sampling rates
+
 pprint(speech_timestamps)
 ```