tipi/kyutai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Support for stereo audio

Browse Source
This commit is contained in:
Christopher Oezbek 2025-07-04 13:37:07 +02:00
parent f8110e3487
commit 6966635499
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
scripts/stt_from_file_pytorch.py
View File

@ -152,6 +152,7 @@ def main(args):
audio, input_sample_rate = sphn.read(args.in_file) audio, input_sample_rate = sphn.read(args.in_file)
audio = torch.from_numpy(audio).to(args.device) audio = torch.from_numpy(audio).to(args.device)
audio = audio.mean(dim=0, keepdim=True) # Convert to mono
audio = julius.resample_frac(audio, input_sample_rate, mimi.sample_rate) audio = julius.resample_frac(audio, input_sample_rate, mimi.sample_rate)
if audio.shape[-1] % mimi.frame_size != 0: if audio.shape[-1] % mimi.frame_size != 0:
to_pad = mimi.frame_size - audio.shape[-1] % mimi.frame_size to_pad = mimi.frame_size - audio.shape[-1] % mimi.frame_size