length fix

infer.py

@@ -16,7 +16,7 @@
 
 def run_clip(svc_model, key, acc, use_pe, use_crepe, thre, use_gt_mel, add_noise_step, project_name='', f_name=None,
              file_path=None, out_path=None,**kwargs):
-    print(f'code version:2022-11-23')
+    print(f'code version:2022-11-23 v2')
     use_pe = use_pe if hparams['audio_sample_rate'] == 24000 else False
     if file_path is None:
         raw_audio_path = f"./raw/{f_name}"
@@ -27,7 +27,7 @@ def run_clip(svc_model, key, acc, use_pe, use_crepe, thre, use_gt_mel, add_noise
     infer_tool.format_wav(raw_audio_path)
     wav_path = Path(raw_audio_path).with_suffix('.wav')
     global chunks_dict
-    audio, sr = librosa.load(wav_path, mono=True)
+    audio, sr = librosa.load(wav_path, mono=True,sr=None)
     wav_hash = infer_tool.get_md5(audio)
     if wav_hash in chunks_dict.keys():
         print("load chunks from temp")
@@ -61,7 +61,7 @@ def run_clip(svc_model, key, acc, use_pe, use_crepe, thre, use_gt_mel, add_noise
                                                         thre=thre, use_gt_mel=use_gt_mel, add_noise_step=add_noise_step)
         fix_audio = np.zeros(length)
         fix_audio[:] = np.mean(_audio)
-        fix_audio[:len(_audio)] = _audio
+        fix_audio[:len(_audio)] = _audio[0 if len(_audio)<len(fix_audio) else len(_audio)-len(fix_audio):]
         f0_tst.extend(_f0_tst)
         f0_pred.extend(_f0_pred)
         audio.extend(list(fix_audio))