Merge pull request #867 from FunAudioLLM/dev/lyuxiang.lx

Dev/lyuxiang.lx

Author: aluminumbox

README.md

@@ -63,7 +63,7 @@ git submodule update --init --recursive
 - Create Conda env:
 
 ``` sh
-conda create -n cosyvoice python=3.10
+conda create -n cosyvoice -y python=3.10
 conda activate cosyvoice
 # pynini is required by WeTextProcessing, use conda to install it as it can be executed on all platform.
 conda install -y -c conda-forge pynini==2.1.5

cosyvoice/utils/file_utils.py

@@ -40,7 +40,7 @@ def read_json_lists(list_file):
 
 
 def load_wav(wav, target_sr):
-    speech, sample_rate = torchaudio.load(wav)
+    speech, sample_rate = torchaudio.load(wav, backend='soundfile')
     speech = speech.mean(dim=0, keepdim=True)
     if sample_rate != target_sr:
         assert sample_rate > target_sr, 'wav sample rate {} must be greater than {}'.format(sample_rate, target_sr)