Mirroristas/whisper
2
0
Fork 0
mirror of https://github.com/openai/whisper.git synced 2025-11-27 15:54:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge ccacb7f5defb139e77a553c2114cf19c63084962 into 173ff7dd1d9fb1c4fddea0d41d704cfefeb8908c

Browse Source
This commit is contained in:
Pavel 2024-11-26 20:45:46 +03:30 committed by GitHub
commit 369480a232
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
whisper/audio.py
View File

@ -122,7 +122,7 @@ def log_mel_spectrogram(
The path to audio or either a NumPy array or Tensor containing the audio waveform in 16 kHz The path to audio or either a NumPy array or Tensor containing the audio waveform in 16 kHz
n_mels: int n_mels: int
The number of Mel-frequency filters, only 80 is supported The number of Mel-frequency filters, only 80 or 128 is supported
padding: int padding: int
Number of zero samples to pad to the right Number of zero samples to pad to the right
@ -132,7 +132,7 @@ def log_mel_spectrogram(
Returns Returns
------- -------
torch.Tensor, shape = (80, n_frames) torch.Tensor, shape = (80, n_frames) or (128, n_frames), depends on n_mels value
A Tensor that contains the Mel spectrogram A Tensor that contains the Mel spectrogram
""" """
if not torch.is_tensor(audio): if not torch.is_tensor(audio):