update

README.md

@@ -134,10 +134,11 @@ 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)
 
-# save zero_shot spk for futher usage
+# save zero_shot spk for future usage
 assert cosyvoice.add_zero_shot_spk('希望你以后能够做的比我还好呦。', prompt_speech_16k, 'my_zero_shot_spk') is True
 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。', '', '', zero_shot_spk_id='my_zero_shot_spk', stream=False)):
     torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+cosyvoice.save_spkinfo()
 
 # fine grained control, for supported control, check cosyvoice/tokenizer/tokenizer.py#L248
 for i, j in enumerate(cosyvoice.inference_cross_lingual('在他讲述那个荒诞故事的过程中，他突然[laughter]停下来，因为他自己也被逗笑了[laughter]。', prompt_speech_16k, stream=False)):

cosyvoice/cli/cosyvoice.py

@@ -74,6 +74,9 @@ class CosyVoice:
         self.frontend.spk2info[zero_shot_spk_id] = model_input
         return True
 
+    def save_spkinfo(self):
+        torch.save(self.frontend.spk2info, '{}/spk2info.pt'.format(self.model_dir))
+
     def inference_sft(self, tts_text, spk_id, stream=False, speed=1.0, text_frontend=True):
         for i in tqdm(self.frontend.text_normalize(tts_text, split=True, text_frontend=text_frontend)):
             model_input = self.frontend.frontend_sft(i, spk_id)