fix inference_instruct2 speaker ID bug

Author: bearlu007

cosyvoice/cli/cosyvoice.py

@@ -177,10 +177,10 @@ def __init__(self, model_dir, load_jit=False, load_trt=False, fp16=False, use_fl
     def inference_instruct(self, *args, **kwargs):
         raise NotImplementedError('inference_instruct is not implemented for CosyVoice2!')
 
-    def inference_instruct2(self, tts_text, instruct_text, prompt_speech_16k, stream=False, speed=1.0, text_frontend=True):
+    def inference_instruct2(self, tts_text, instruct_text, prompt_speech_16k, zero_shot_spk_id='', stream=False, speed=1.0, text_frontend=True):
         assert isinstance(self.model, CosyVoice2Model), 'inference_instruct2 is only implemented for CosyVoice2!'
         for i in tqdm(self.frontend.text_normalize(tts_text, split=True, text_frontend=text_frontend)):
-            model_input = self.frontend.frontend_instruct2(i, instruct_text, prompt_speech_16k, self.sample_rate)
+            model_input = self.frontend.frontend_instruct2(i, instruct_text, prompt_speech_16k, self.sample_rate, zero_shot_spk_id)
             start_time = time.time()
             logging.info('synthesis text {}'.format(i))
             for model_output in self.model.tts(**model_input, stream=stream, speed=speed):

cosyvoice/cli/frontend.py

@@ -196,8 +196,8 @@ def frontend_instruct(self, tts_text, spk_id, instruct_text):
         model_input['prompt_text_len'] = instruct_text_token_len
         return model_input
 
-    def frontend_instruct2(self, tts_text, instruct_text, prompt_speech_16k, resample_rate):
-        model_input = self.frontend_zero_shot(tts_text, instruct_text + '<|endofprompt|>', prompt_speech_16k, resample_rate)
+    def frontend_instruct2(self, tts_text, instruct_text, prompt_speech_16k, resample_rate, zero_shot_spk_id):
+        model_input = self.frontend_zero_shot(tts_text, instruct_text + '<|endofprompt|>', prompt_speech_16k, resample_rate, zero_shot_spk_id)
         del model_input['llm_prompt_speech_token']
         del model_input['llm_prompt_speech_token_len']
         return model_input

test1.py

@@ -0,0 +1,37 @@
+import sys
+sys.path.append('third_party/Matcha-TTS')
+from cosyvoice.cli.cosyvoice import CosyVoice, CosyVoice2
+from cosyvoice.utils.file_utils import load_wav
+import torchaudio # type: ignore
+
+cosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=False, load_trt=False, fp16=False, use_flow_cache=False)
+
+# 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('./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 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)):
+    torchaudio.save('fine_grained_control_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+
+# instruct usage
+for i, j in enumerate(cosyvoice.inference_instruct2('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。', '用四川话说这句话', prompt_speech_16k, stream=False)):
+    torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+
+# bistream usage, you can use generator as input, this is useful when using text llm model as input
+# NOTE you should still have some basic sentence split logic because llm can not handle arbitrary sentence length
+def text_generator():
+    yield '收到好友从远方寄来的生日礼物，'
+    yield '那份意外的惊喜与深深的祝福'
+    yield '让我心中充满了甜蜜的快乐，'
+    yield '笑容如花儿般绽放。'
+for i, j in enumerate(cosyvoice.inference_zero_shot(text_generator(), '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)