update

README.md

@@ -1,42 +1,51 @@
-# CosyVoice
-
-## 👉🏻 [CosyVoice2 Demos](https://funaudiollm.github.io/cosyvoice2/) 👈🏻
-[[CosyVoice2 Paper](https://fun-audio-llm.github.io/pdf/CosyVoice_v1.pdf)][[CosyVoice2 Studio](https://www.modelscope.cn/studios/iic/CosyVoice2-0.5B)]
-
-## 👉🏻 [CosyVoice Demos](https://fun-audio-llm.github.io/) 👈🏻
-[[CosyVoice Paper](https://fun-audio-llm.github.io/pdf/CosyVoice_v1.pdf)][[CosyVoice Studio](https://www.modelscope.cn/studios/iic/CosyVoice-300M)][[CosyVoice Code](https://github.com/FunAudioLLM/CosyVoice)]
-
-For `SenseVoice`, visit [SenseVoice repo](https://github.com/FunAudioLLM/SenseVoice) and [SenseVoice space](https://www.modelscope.cn/studios/iic/SenseVoice).
+[![SVG Banners](https://svg-banners.vercel.app/api?type=origin&text1=CosyVoice🤠&text2=Text-to-Speech%20💖%20Large%20Language%20Model&width=800&height=210)](https://github.com/Akshay090/svg-banners)
+
+## 👉🏻 CosyVoice 👈🏻
+**CosyVoice 2.0**: [Demos](https://funaudiollm.github.io/cosyvoice2/); [Paper](https://funaudiollm.github.io/pdf/CosyVoice_2.pdf); [Modelscope](https://www.modelscope.cn/studios/iic/CosyVoice2-0.5B)
+
+**CosyVoice 1.0**: [Demos](https://fun-audio-llm.github.io); [Paper](https://funaudiollm.github.io/pdf/CosyVoice_v1.pdf); [Modelscope](https://www.modelscope.cn/studios/iic/CosyVoice-300M)
+
+## Highlight🔥
+
+**CosyVoice 2.0** has been released! Compared to version 1.0, the new version offers more accurate, more stable, faster, and better speech generation capabilities.
+### Multilingual
+- **Support Language**: Chinese, English, Japanese, Korean, Chinese dialects (Cantonese, Sichuanese, Shanghainese, Tianjinese, Wuhanese, etc.)
+- **Crosslingual & Mixlingual**：Support zero-shot voice cloning for cross-lingual and code-switching scenarios.
+### Ultra-Low Latency
+- **Bidirectional Streaming Support**: CosyVoice 2.0 integrates offline and streaming modeling technologies.
+- **Rapid First Packet Synthesis**: Achieves latency as low as 150ms while maintaining high-quality audio output.
+### High Accuracy
+- **Improved Pronunciation**: Reduces pronunciation errors by 30% to 50% compared to CosyVoice 1.0.
+- **Benchmark Achievements**: Attains the lowest character error rate on the hard test set of the Seed-TTS evaluation set.
+### Strong Stability
+- **Consistency in Timbre**: Ensures reliable voice consistency for zero-shot and cross-language speech synthesis.
+- **Cross-language Synthesis**: Marked improvements compared to version 1.0.
+### Natural Experience
+- **Enhanced Prosody and Sound Quality**: Improved alignment of synthesized audio, raising MOS evaluation scores from 5.4 to 5.53.
+- **Emotional and Dialectal Flexibility**: Now supports more granular emotional controls and accent adjustments.
 
 ## Roadmap
 
 - [x] 2024/12
 
-    - [x] CosyVoice2-0.5B model release
-    - [x] CosyVoice2-0.5B streaming inference with no quality degradation
+    - [x] 25hz cosyvoice 2.0 released
 
-- [x] 2024/07
+- [x] 2024/09
 
-    - [x] Flow matching training support
-    - [x] WeTextProcessing support when ttsfrd is not avaliable
-    - [x] Fastapi server and client
+    - [x] 25hz cosyvoice base model
+    - [x] 25hz cosyvoice voice conversion model
 
 - [x] 2024/08
 
     - [x] Repetition Aware Sampling(RAS) inference for llm stability
     - [x] Streaming inference mode support, including kv cache and sdpa for rtf optimization
 
-- [x] 2024/09
-
-    - [x] 25hz cosyvoice base model
-    - [x] 25hz cosyvoice voice conversion model
+- [x] 2024/07
 
-- [ ] TBD
+    - [x] Flow matching training support
+    - [x] WeTextProcessing support when ttsfrd is not avaliable
+    - [x] Fastapi server and client
 
-    - [ ] CosyVoice2-0.5B bistream inference support
-    - [ ] CosyVoice2-0.5B training and finetune recipie
-    - [ ] CosyVoice-500M trained with more multi-lingual data
-    - [ ] More...
 
 ## Install
 
@@ -54,7 +63,7 @@ git submodule update --init --recursive
 - Create Conda env:
 
 ``` sh
-conda create -n cosyvoice python=3.10
+conda create -n cosyvoice python=3.8
 conda activate cosyvoice
 # pynini is required by WeTextProcessing, use conda to install it as it can be executed on all platform.
 conda install -y -c conda-forge pynini==2.1.5
@@ -102,16 +111,16 @@ Notice that this step is not necessary. If you do not install `ttsfrd` package,
 ``` sh
 cd pretrained_models/CosyVoice-ttsfrd/
 unzip resource.zip -d .
-pip install ttsfrd-0.3.6-cp38-cp38-linux_x86_64.whl
+pip install ttsfrd_dependency-0.1-py3-none-any.whl
+pip install ttsfrd-0.4.2-cp310-cp310-linux_x86_64.whl
 ```
 
 **Basic Usage**
 
-For zero_shot/cross_lingual inference, please use `CosyVoice2-0.5B` or `CosyVoice-300M` model.
+We strongly recommend using `CosyVoice2-0.5B` for better performance.
+For zero_shot/cross_lingual inference, please use `CosyVoice-300M` model.
 For sft inference, please use `CosyVoice-300M-SFT` model.
 For instruct inference, please use `CosyVoice-300M-Instruct` model.
-We strongly recommend using `CosyVoice2-0.5B` model for better streaming performance.
-
 First, add `third_party/Matcha-TTS` to your `PYTHONPATH`.
 
 ``` sh
@@ -123,14 +132,15 @@ from cosyvoice.cli.cosyvoice import CosyVoice, CosyVoice2
 from cosyvoice.utils.file_utils import load_wav
 import torchaudio
 
-## cosyvoice2 usage
-cosyvoice2 = CosyVoice('pretrained_models/CosyVoice2-0.5B', load_jit=False, load_onnx=False, load_trt=False)
+# cosyvoice2
+cosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=True, load_onnx=False, load_trt=False)
+
 # zero_shot usage
 prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
-for i, j in enumerate(cosyvoice2.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=True)):
-    torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice2.sample_rate)
+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)
 
-## cosyvoice usage
+# cosyvoice
 cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=True, load_onnx=False, fp16=True)
 # sft usage
 print(cosyvoice.list_avaliable_spks())
@@ -209,16 +219,5 @@ You can also scan the QR code to join our official Dingding chat group.
 4. We borrowed a lot of code from [AcademiCodec](https://github.com/yangdongchao/AcademiCodec).
 5. We borrowed a lot of code from [WeNet](https://github.com/wenet-e2e/wenet).
 
-## Citations
-
-``` bibtex
-@article{du2024cosyvoice,
-  title={Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens},
-  author={Du, Zhihao and Chen, Qian and Zhang, Shiliang and Hu, Kai and Lu, Heng and Yang, Yexin and Hu, Hangrui and Zheng, Siqi and Gu, Yue and Ma, Ziyang and others},
-  journal={arXiv preprint arXiv:2407.05407},
-  year={2024}
-}
-```
-
 ## Disclaimer
 The content provided above is for academic purposes only and is intended to demonstrate technical capabilities. Some examples are sourced from the internet. If any content infringes on your rights, please contact us to request its removal.

cosyvoice/cli/frontend.py

@@ -12,6 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 from functools import partial
+import json
 import onnxruntime
 import torch
 import numpy as np
@@ -66,9 +67,7 @@ class CosyVoiceFrontEnd:
             ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
             assert self.frd.initialize('{}/../../pretrained_models/CosyVoice-ttsfrd/resource'.format(ROOT_DIR)) is True, \
                 'failed to initialize ttsfrd resource'
-            self.frd.set_lang_type('pinyin')
-            self.frd.enable_pinyin_mix(True)
-            self.frd.set_breakmodel_index(1)
+            self.frd.set_lang_type('pinyinvg')
         else:
             self.zh_tn_model = ZhNormalizer(remove_erhua=False, full_to_half=False)
             self.en_tn_model = EnNormalizer()
@@ -112,26 +111,28 @@ class CosyVoiceFrontEnd:
         text = text.strip()
         if contains_chinese(text):
             if self.use_ttsfrd:
-                text = self.frd.get_frd_extra_info(text, 'input')
+                texts = [i["text"] for i in json.loads(self.frd.do_voicegen_frd(text))["sentences"]]
+                text = ''.join(texts)
             else:
                 text = self.zh_tn_model.normalize(text)
-            text = text.replace("\n", "")
-            text = replace_blank(text)
-            text = replace_corner_mark(text)
-            text = text.replace(".", "。")
-            text = text.replace(" - ", "，")
-            text = remove_bracket(text)
-            text = re.sub(r'[，,、]+$', '。', text)
-            texts = list(split_paragraph(text, partial(self.tokenizer.encode, allowed_special=self.allowed_special), "zh", token_max_n=80,
-                                         token_min_n=60, merge_len=20, comma_split=False))
+                text = text.replace("\n", "")
+                text = replace_blank(text)
+                text = replace_corner_mark(text)
+                text = text.replace(".", "。")
+                text = text.replace(" - ", "，")
+                text = remove_bracket(text)
+                text = re.sub(r'[，,、]+$', '。', text)
+                texts = list(split_paragraph(text, partial(self.tokenizer.encode, allowed_special=self.allowed_special), "zh", token_max_n=80,
+                                            token_min_n=60, merge_len=20, comma_split=False))
         else:
             if self.use_ttsfrd:
-                text = self.frd.get_frd_extra_info(text, 'input')
+                texts = [i["text"] for i in json.loads(self.frd.do_voicegen_frd(text))["sentences"]]
+                text = ''.join(texts)
             else:
                 text = self.en_tn_model.normalize(text)
-            text = spell_out_number(text, self.inflect_parser)
-            texts = list(split_paragraph(text, partial(self.tokenizer.encode, allowed_special=self.allowed_special), "en", token_max_n=80,
-                                         token_min_n=60, merge_len=20, comma_split=False))
+                text = spell_out_number(text, self.inflect_parser)
+                texts = list(split_paragraph(text, partial(self.tokenizer.encode, allowed_special=self.allowed_special), "en", token_max_n=80,
+                                            token_min_n=60, merge_len=20, comma_split=False))
         if split is False:
             return text
         return texts