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

align others with dev_gzf_deepspeed

Browse Source
This commit is contained in:
志浩 2024-09-18 18:10:07 +08:00
parent 669fedef82
commit 7edf6a30d9
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
funasr/models/llm_asr/model.py
View File

@ -3238,7 +3238,7 @@ class LLMASRXvecSlotTTS(nn.Module):
token_list.append(cur_token)
feat_list.append(feat)
# we should return this data to web page for playing.
mp3_data = self.convert_wav_to_mp3(wav)
mp3_data = self.convert_wav_to_mp3(wav, is_last)
wav_list.append(wav)
mp3_list.append(mp3_data)
@ -3301,7 +3301,7 @@ class LLMASRXvecSlotTTS(nn.Module):
states["chunk_idx"] = chunk_idx
if format == "mp3":
if cur_token is not None:
wav = self.convert_wav_to_mp3(wav)
wav = self.convert_wav_to_mp3(wav, is_last)
return cur_token, feat, wav
def simple_streaming_generate_speech(
@ -3344,7 +3344,7 @@ class LLMASRXvecSlotTTS(nn.Module):
states["chunk_idx"] = chunk_idx
if format == "mp3":
if cur_token is not None:
wav = self.convert_wav_to_mp3(wav)
wav = self.convert_wav_to_mp3(wav, is_last)
return cur_token, feat, wav
def write_mel_wav(self, output_dir, feat, wav, mp3, key):