Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

wenetspeech

游雁0b764d335067
diff --git a/funasr/bin/compute_audio_cmvn.py b/funasr/bin/compute_audio_cmvn.py
index 697da94bb..20c8e0ded 100644
--- a/funasr/bin/compute_audio_cmvn.py
+++ b/funasr/bin/compute_audio_cmvn.py
@@ -75,6 +75,7 @@ def main(**kwargs):
if batch_idx % log_step == 0:
print(f"prcessed: {batch_idx}/{iter_stop}")
if batch_idx >= iter_stop and iter_stop > 0.0:
+ print(f"prcessed: {iter_stop}/{iter_stop}")
break
fbank = batch["speech"].numpy()[0, :, :]