speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix volume bug for mp3 converter

Browse Source
This commit is contained in:
志浩 2024-09-12 16:54:46 +08:00
parent cce50009b0
commit 3cfffe28a7
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
funasr/models/llm_asr/model.py
View File

@ -3050,8 +3050,8 @@ class LLMASRXvecSlotTTS(nn.Module):
def convert_wav_to_mp3(self, wav: torch.Tensor):
wav = wav.detach().cpu().numpy()
wav = (wav * (2**16-1)).astype(np.int16)
mp3 = AudioSegment.from_raw(
wav = (wav * (2**15-1) * 0.8).astype(np.int16)
mp3 = AudioSegment(
wav.tobytes(),
sample_width=16 // 8, # Sample width in bytes
frame_rate=22050,