Merge pull request #375 from zhang-heng/main

fix: 语音切分list文件乱序

tools/damo_asr/cmd-asr.py

@@ -25,7 +25,9 @@ model = AutoModel(model=path_asr, model_revision="v2.0.4",
 
 
 opt=[]
-for name in os.listdir(dir):
+file_names = os.listdir(dir)
+file_names.sort()
+for name in file_names:
     try:
         text = model.generate(input="%s/%s"%(dir,name))[0]["text"]
         opt.append("%s/%s|%s|ZH|%s"%(dir,name,opt_name,text))

tools/slice_audio.py

@@ -35,7 +35,7 @@ def slice(inp,opt_root,threshold,min_length,min_interval,hop_size,max_sil_kept,_
                 if(tmp_max>1):chunk/=tmp_max
                 chunk = (chunk / tmp_max * (_max * alpha)) + (1 - alpha) * chunk
                 wavfile.write(
-                    "%s/%s_%s_%s.wav" % (opt_root, name, start, end),
+                    "%s/%s_%010d_%010d.wav" % (opt_root, name, start, end),
                     32000,
                     # chunk.astype(np.float32),
                     (chunk * 32767).astype(np.int16),