LLM/WhisperLiveKit
1
0
Fork 0
mirror of https://github.com/QuentinFuxa/WhisperLiveKit.git synced 2026-03-07 14:23:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #211 from Alexander-ARTV/main

Browse Source 
Fix type error when setting encoder_feature in simul_whisper->infer for faster whisper encoder
This commit is contained in:
Quentin Fuxa
2025-09-09 15:46:59 +02:00
committed by GitHub
parent f661f21675 3358877054
commit da8726b2cb
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
whisperlivekit/simul_whisper/simul_whisper.py
View File

@@ -408,8 +408,13 @@ class PaddedAlignAttWhisper:
content_mel_len = int(audio_length_seconds * 100)//2
mel_padded_2 = self.fw_feature_extractor(waveform=input_segments.numpy(), padding=N_SAMPLES)[None, :]
mel = fw_pad_or_trim(mel_padded_2, N_FRAMES, axis=-1)
encoder_feature_ctranslate = np.array(self.fw_encoder.encode(mel))
encoder_feature = torch.as_tensor(encoder_feature_ctranslate, device=self.device)
encoder_feature_ctranslate = self.fw_encoder.encode(mel)
if self.device == 'cpu': #it seems that on gpu, passing StorageView to torch.as_tensor fails and wrapping in the array works
encoder_feature_ctranslate = np.array(encoder_feature_ctranslate)
try:
encoder_feature = torch.as_tensor(encoder_feature_ctranslate, device=self.device)
except TypeError: # Normally the cpu condition should prevent having exceptions, but just in case:
encoder_feature = torch.as_tensor(np.array(encoder_feature_ctranslate), device=self.device)
else:
# mel + padding to 30s
mel_padded = log_mel_spectrogram(input_segments, n_mels=self.model.dims.n_mels, padding=N_SAMPLES,