Merge pull request #868 from FunAudioLLM/dev/lyuxiang.lx

move prompt wav to asset

Author: aluminumbox

README.md

@@ -132,7 +132,7 @@ cosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=False, load
 
 # NOTE if you want to reproduce the results on https://funaudiollm.github.io/cosyvoice2, please add text_frontend=False during inference
 # zero_shot usage
-prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
+prompt_speech_16k = load_wav('./asset/zero_shot_prompt.wav', 16000)
 for i, j in enumerate(cosyvoice.inference_zero_shot('收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般绽放。', '希望你以后能够做的比我还好呦。', prompt_speech_16k, stream=False)):
     torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
 
@@ -156,16 +156,16 @@ for i, j in enumerate(cosyvoice.inference_sft('你好，我是通义生成式语
 
 cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M') # or change to pretrained_models/CosyVoice-300M-25Hz for 25Hz inference
 # zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
-prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
+prompt_speech_16k = load_wav('./asset/zero_shot_prompt.wav', 16000)
 for i, j in enumerate(cosyvoice.inference_zero_shot('收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般绽放。', '希望你以后能够做的比我还好呦。', prompt_speech_16k, stream=False)):
     torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
 # cross_lingual usage
-prompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
+prompt_speech_16k = load_wav('./asset/cross_lingual_prompt.wav', 16000)
 for i, j in enumerate(cosyvoice.inference_cross_lingual('<|en|>And then later on, fully acquiring that company. So keeping management in line, interest in line with the asset that\'s coming into the family is a reason why sometimes we don\'t buy the whole thing.', prompt_speech_16k, stream=False)):
     torchaudio.save('cross_lingual_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
 # vc usage
-prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
-source_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
+prompt_speech_16k = load_wav('./asset/zero_shot_prompt.wav', 16000)
+source_speech_16k = load_wav('./asset/cross_lingual_prompt.wav', 16000)
 for i, j in enumerate(cosyvoice.inference_vc(source_speech_16k, prompt_speech_16k, stream=False)):
     torchaudio.save('vc_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
 

cross_lingual_prompt.wav renamed to asset/cross_lingual_prompt.wav

@@ -79,7 +79,7 @@ def main():
                         default='希望你以后能够做的比我还好呦。')
     parser.add_argument('--prompt_wav',
                         type=str,
-                        default='../../../zero_shot_prompt.wav')
+                        default='../../../asset/zero_shot_prompt.wav')
     parser.add_argument('--instruct_text',
                         type=str,
                         default='Theo \'Crimson\', is a fiery, passionate rebel leader. \

zero_shot_prompt.wav renamed to asset/zero_shot_prompt.wav

@@ -93,7 +93,7 @@ def main():
                         default='希望你以后能够做的比我还好呦。')
     parser.add_argument('--prompt_wav',
                         type=str,
-                        default='../../../zero_shot_prompt.wav')
+                        default='../../../asset/zero_shot_prompt.wav')
     parser.add_argument('--instruct_text',
                         type=str,
                         default='Theo \'Crimson\', is a fiery, passionate rebel leader. \