remove unncessary code

README.md

@@ -101,7 +101,7 @@ We strongly recommend that you download our pretrained `CosyVoice2-0.5B` `CosyVo
 ``` python
 # SDK模型下载
 from modelscope import snapshot_download
-snapshot_download('iic/CosyVoice3-0.5B', local_dir='pretrained_models/CosyVoice3-0.5B')
+snapshot_download('FunAudioLLM/Fun-CosyVoice3-0.5B', local_dir='pretrained_models/Fun-CosyVoice3-0.5B')
 snapshot_download('iic/CosyVoice2-0.5B', local_dir='pretrained_models/CosyVoice2-0.5B')
 snapshot_download('iic/CosyVoice-300M', local_dir='pretrained_models/CosyVoice-300M')
 snapshot_download('iic/CosyVoice-300M-SFT', local_dir='pretrained_models/CosyVoice-300M-SFT')

cosyvoice/cli/cosyvoice.py

@@ -27,7 +27,6 @@ from cosyvoice.utils.class_utils import get_model_type
 class CosyVoice:
 
     def __init__(self, model_dir, load_jit=False, load_trt=False, fp16=False, trt_concurrent=1):
-        self.instruct = True if '-Instruct' in model_dir else False
         self.model_dir = model_dir
         self.fp16 = fp16
         if not os.path.exists(model_dir):
@@ -37,7 +36,7 @@ class CosyVoice:
             raise ValueError('{} not found!'.format(hyper_yaml_path))
         with open(hyper_yaml_path, 'r') as f:
             configs = load_hyperpyyaml(f)
-        assert get_model_type(configs) != CosyVoice2Model, 'do not use {} for CosyVoice initialization!'.format(model_dir)
+        assert get_model_type(configs) == CosyVoiceModel, 'do not use {} for CosyVoice initialization!'.format(model_dir)
         self.frontend = CosyVoiceFrontEnd(configs['get_tokenizer'],
                                           configs['feat_extractor'],
                                           '{}/campplus.onnx'.format(model_dir),
@@ -116,8 +115,6 @@ class CosyVoice:
 
     def inference_instruct(self, tts_text, spk_id, instruct_text, stream=False, speed=1.0, text_frontend=True):
         assert isinstance(self.model, CosyVoiceModel), 'inference_instruct is only implemented for CosyVoice!'
-        if self.instruct is False:
-            raise ValueError('{} do not support instruct inference'.format(self.model_dir))
         instruct_text = self.frontend.text_normalize(instruct_text, split=False, text_frontend=text_frontend)
         for i in tqdm(self.frontend.text_normalize(tts_text, split=True, text_frontend=text_frontend)):
             model_input = self.frontend.frontend_instruct(i, spk_id, instruct_text)
@@ -142,7 +139,6 @@ class CosyVoice:
 class CosyVoice2(CosyVoice):
 
     def __init__(self, model_dir, load_jit=False, load_trt=False, load_vllm=False, fp16=False, trt_concurrent=1):
-        self.instruct = True if '-Instruct' in model_dir else False
         self.model_dir = model_dir
         self.fp16 = fp16
         if not os.path.exists(model_dir):
@@ -197,7 +193,6 @@ class CosyVoice2(CosyVoice):
 class CosyVoice3(CosyVoice2):
 
     def __init__(self, model_dir, load_trt=False, load_vllm=False, fp16=False, trt_concurrent=1):
-        self.instruct = True if '-Instruct' in model_dir else False
         self.model_dir = model_dir
         self.fp16 = fp16
         if not os.path.exists(model_dir):

example.py

@@ -1,7 +1,6 @@
 import sys
 sys.path.append('third_party/Matcha-TTS')
 from cosyvoice.cli.cosyvoice import AutoModel
-from cosyvoice.utils.file_utils import load_wav
 import torchaudio
 
 
@@ -68,7 +67,7 @@ def cosyvoice2_example():
 def cosyvoice3_example():
     """ CosyVoice3 Usage, check https://funaudiollm.github.io/cosyvoice3/ for more details
     """
-    cosyvoice = AutoModel(model_dir='pretrained_models/CosyVoice3-0.5B')
+    cosyvoice = AutoModel(model_dir='pretrained_models/Fun-CosyVoice3-0.5B')
     # zero_shot usage
     for i, j in enumerate(cosyvoice.inference_zero_shot('八百标兵奔北坡，北坡炮兵并排跑，炮兵怕把标兵碰，标兵怕碰炮兵炮。', 'You are a helpful assistant.<|endofprompt|>希望你以后能够做的比我还好呦。', './asset/zero_shot_prompt.wav', stream=False)):
         torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
@@ -77,7 +76,7 @@ def cosyvoice3_example():
     for i, j in enumerate(cosyvoice.inference_cross_lingual('You are a helpful assistant.<|endofprompt|>[breath]因为他们那一辈人[breath]在乡里面住的要习惯一点，[breath]邻居都很活络，[breath]嗯，都很熟悉。[breath]', './asset/zero_shot_prompt.wav', stream=False)):
         torchaudio.save('fine_grained_control_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
 
-    # instruct usage
+    # instruct usage, for supported control, check cosyvoice/utils/common.py#L28
     for i, j in enumerate(cosyvoice.inference_instruct2('好少咯，一般系放嗰啲国庆啊，中秋嗰啲可能会咯。', 'You are a helpful assistant. 请用广东话表达。<|endofprompt|>', './asset/zero_shot_prompt.wav', stream=False)):
         torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
     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。', 'You are a helpful assistant. 请用尽可能快地语速说一句话。<|endofprompt|>', './asset/zero_shot_prompt.wav', stream=False)):

vllm_example.py

@@ -21,7 +21,7 @@ def cosyvoice2_example():
 def cosyvoice3_example():
     """ CosyVoice3 vllm usage
     """
-    cosyvoice = AutoModel(model_dir='pretrained_models/CosyVoice3-0.5B', load_trt=True, load_vllm=True, fp16=False)
+    cosyvoice = AutoModel(model_dir='pretrained_models/Fun-CosyVoice3-0.5B', load_trt=True, load_vllm=True, fp16=False)
     for i in tqdm(range(100)):
         set_all_random_seed(i)
         for _, _ 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。', 'You are a helpful assistant.<|endofprompt|>希望你以后能够做的比我还好呦。', './asset/zero_shot_prompt.wav', stream=False)):