update

.gitattributes

@@ -45,3 +45,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+speech_tokenizer_v3.onnx filter=lfs diff=lfs merge=lfs -text
+llm.pt filter=lfs diff=lfs merge=lfs -text
+flow.pt filter=lfs diff=lfs merge=lfs -text
+hift.pt filter=lfs diff=lfs merge=lfs -text
+flow.decoder.estimator.fp32.onnx filter=lfs diff=lfs merge=lfs -text
+CosyVoice-BlankEN/model.safetensors filter=lfs diff=lfs merge=lfs -text
+campplus.onnx filter=lfs diff=lfs merge=lfs -text

CosyVoice-BlankEN/config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

CosyVoice-BlankEN/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

CosyVoice-BlankEN/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

README.md

@@ -1,52 +1,237 @@
----
-frameworks:
-- Pytorch
-license: Apache License 2.0
-tags: []
-tasks:
-- text-to-speech
+[![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)
 
-#model-type:
-##如 gpt、phi、llama、chatglm、baichuan 等
-#- gpt
+## 👉🏻 CosyVoice 👈🏻
 
-#domain:
-##如 nlp、cv、audio、multi-modal
-#- nlp
+**CosyVoice 3.0**: [Demos](https://funaudiollm.github.io/cosyvoice3/); [Paper](https://arxiv.org/abs/2505.17589); [Modelscope](https://www.modelscope.cn/studios/FunAudioLLM/Fun-CosyVoice3-0.5B); [CV3-Eval](https://github.com/FunAudioLLM/CV3-Eval)
 
-#language:
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
-#- cn 
+**CosyVoice 2.0**: [Demos](https://funaudiollm.github.io/cosyvoice2/); [Paper](https://arxiv.org/abs/2412.10117); [Modelscope](https://www.modelscope.cn/studios/iic/CosyVoice2-0.5B); [HuggingFace](https://huggingface.co/spaces/FunAudioLLM/CosyVoice2-0.5B)
 
-#metrics:
-##如 CIDEr、Blue、ROUGE 等
-#- CIDEr
+**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)
 
-#tags:
-##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
-#- pretrained
+## Highlight🔥
 
-#tools:
-##如 vllm、fastchat、llamacpp、AdaSeq 等
-#- vllm
----
-### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
+**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
+- **Supported 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.
 
-SDK下载
-```bash
-#安装ModelScope
-pip install modelscope
+## Roadmap
+
+- [x] 2025/12
+
+    - [x] release CosyVoice3-0.5B base model and its training/inference script
+    - [x] release CosyVoice3-0.5B modelscope gradio space
+
+- [x] 2025/08
+
+    - [x] Thanks to the contribution from NVIDIA Yuekai Zhang, add triton trtllm runtime support and cosyvoice2 grpo training support
+
+- [x] 2025/07
+
+    - [x] release CosyVoice 3.0 eval set
+
+- [x] 2025/05
+
+    - [x] add CosyVoice2-0.5B vllm support
+
+- [x] 2024/12
+
+    - [x] 25hz CosyVoice2-0.5B released
+
+- [x] 2024/09
+
+    - [x] 25hz CosyVoice-300M base model
+    - [x] 25hz CosyVoice-300M voice conversion function
+
+- [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] 2024/07
+
+    - [x] Flow matching training support
+    - [x] WeTextProcessing support when ttsfrd is not available
+    - [x] Fastapi server and client
+
+
+## Install
+
+### Clone and install
+
+- Clone the repo
+    ``` sh
+    git clone --recursive https://github.com/FunAudioLLM/CosyVoice.git
+    # If you failed to clone the submodule due to network failures, please run the following command until success
+    cd CosyVoice
+    git submodule update --init --recursive
     ```
+
+- Install Conda: please see https://docs.conda.io/en/latest/miniconda.html
+- Create Conda env:
+
+    ``` sh
+    conda create -n cosyvoice -y python=3.10
+    conda activate cosyvoice
+    pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
+
+    # If you encounter sox compatibility issues
+    # ubuntu
+    sudo apt-get install sox libsox-dev
+    # centos
+    sudo yum install sox sox-devel
+    ```
+
+### Model download
+
+We strongly recommend that you download our pretrained `CosyVoice2-0.5B` `CosyVoice-300M` `CosyVoice-300M-SFT` `CosyVoice-300M-Instruct` model and `CosyVoice-ttsfrd` resource.
+
 ``` python
 # SDK模型下载
 from modelscope import snapshot_download
-model_dir = snapshot_download('FunAudioLLM/Fun-CosyVoice3-0.5B')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/FunAudioLLM/Fun-CosyVoice3-0.5B.git
+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')
+snapshot_download('iic/CosyVoice-300M-Instruct', local_dir='pretrained_models/CosyVoice-300M-Instruct')
+snapshot_download('iic/CosyVoice-ttsfrd', local_dir='pretrained_models/CosyVoice-ttsfrd')
 ```
 
-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
+Optionally, you can unzip `ttsfrd` resource and install `ttsfrd` package for better text normalization performance.
+
+Notice that this step is not necessary. If you do not install `ttsfrd` package, we will use wetext by default.
+
+``` sh
+cd pretrained_models/CosyVoice-ttsfrd/
+unzip resource.zip -d .
+pip install ttsfrd_dependency-0.1-py3-none-any.whl
+pip install ttsfrd-0.4.2-cp310-cp310-linux_x86_64.whl
+```
+
+### Basic Usage
+
+We strongly recommend using `CosyVoice3-0.5B` for better performance.
+Follow the code in `example.py` for detailed usage of each model.
+```sh
+python example.py
+```
+
+#### CosyVoice2 vllm Usage
+If you want to use vllm for inference, please install `vllm==v0.9.0`. Older vllm version do not support CosyVoice2 inference.
+
+Notice that `vllm==v0.9.0` has a lot of specific requirements, for example `torch==2.7.0`. You can create a new env to in case your hardward do not support vllm and old env is corrupted.
+
+``` sh
+conda create -n cosyvoice_vllm --clone cosyvoice
+conda activate cosyvoice_vllm
+pip install vllm==v0.9.0 transformers==4.51.3 -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
+python vllm_example.py
+```
+
+#### Start web demo
+
+You can use our web demo page to get familiar with CosyVoice quickly.
+
+Please see the demo website for details.
+
+``` python
+# change iic/CosyVoice-300M-SFT for sft inference, or iic/CosyVoice-300M-Instruct for instruct inference
+python3 webui.py --port 50000 --model_dir pretrained_models/CosyVoice-300M
+```
+
+#### Advanced Usage
+
+For advanced users, we have provided training and inference scripts in `examples/libritts/cosyvoice/run.sh`.
+
+#### Build for deployment
+
+Optionally, if you want service deployment,
+You can run the following steps.
+
+``` sh
+cd runtime/python
+docker build -t cosyvoice:v1.0 .
+# change iic/CosyVoice-300M to iic/CosyVoice-300M-Instruct if you want to use instruct inference
+# for grpc usage
+docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/grpc && python3 server.py --port 50000 --max_conc 4 --model_dir iic/CosyVoice-300M && sleep infinity"
+cd grpc && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>
+# for fastapi usage
+docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/fastapi && python3 server.py --port 50000 --model_dir iic/CosyVoice-300M && sleep infinity"
+cd fastapi && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>
+```
+
+#### Using Nvidia TensorRT-LLM for deployment
+
+Using TensorRT-LLM to accelerate cosyvoice2 llm could give 4x acceleration comparing with huggingface transformers implementation.
+To quick start:
+
+``` sh
+cd runtime/triton_trtllm
+docker compose up -d
+```
+For more details, you could check [here](https://github.com/FunAudioLLM/CosyVoice/tree/main/runtime/triton_trtllm)
+
+## Discussion & Communication
+
+You can directly discuss on [Github Issues](https://github.com/FunAudioLLM/CosyVoice/issues).
+
+You can also scan the QR code to join our official Dingding chat group.
+
+<img src="./asset/dingding.png" width="250px">
+
+## Acknowledge
+
+1. We borrowed a lot of code from [FunASR](https://github.com/modelscope/FunASR).
+2. We borrowed a lot of code from [FunCodec](https://github.com/modelscope/FunCodec).
+3. We borrowed a lot of code from [Matcha-TTS](https://github.com/shivammehta25/Matcha-TTS).
+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}
+}
+
+@article{du2024cosyvoice,
+  title={Cosyvoice 2: Scalable streaming speech synthesis with large language models},
+  author={Du, Zhihao and Wang, Yuxuan and Chen, Qian and Shi, Xian and Lv, Xiang and Zhao, Tianyu and Gao, Zhifu and Yang, Yexin and Gao, Changfeng and Wang, Hui and others},
+  journal={arXiv preprint arXiv:2412.10117},
+  year={2024}
+}
+
+@article{du2025cosyvoice,
+  title={CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training},
+  author={Du, Zhihao and Gao, Changfeng and Wang, Yuxuan and Yu, Fan and Zhao, Tianyu and Wang, Hao and Lv, Xiang and Wang, Hui and Shi, Xian and An, Keyu and others},
+  journal={arXiv preprint arXiv:2505.17589},
+  year={2025}
+}
+
+@inproceedings{lyu2025build,
+  title={Build LLM-Based Zero-Shot Streaming TTS System with Cosyvoice},
+  author={Lyu, Xiang and Wang, Yuxuan and Zhao, Tianyu and Wang, Hao and Liu, Huadai and Du, Zhihao},
+  booktitle={ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={1--2},
+  year={2025},
+  organization={IEEE}
+}
+```
+
+## 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.

cosyvoice3.yaml

@@ -0,0 +1,223 @@
+# set random seed, so that you may reproduce your result.
+__set_seed1: !apply:random.seed [1986]
+__set_seed2: !apply:numpy.random.seed [1986]
+__set_seed3: !apply:torch.manual_seed [1986]
+__set_seed4: !apply:torch.cuda.manual_seed_all [1986]
+
+# fixed params
+sample_rate: 24000
+llm_input_size: 896
+llm_output_size: 896
+spk_embed_dim: 192
+qwen_pretrain_path: ''
+token_frame_rate: 25
+token_mel_ratio: 2
+
+# stream related params
+chunk_size: 25 # streaming inference chunk size, in token
+num_decoding_left_chunks: -1 # streaming inference flow decoder left chunk size, <0 means use all left chunks
+
+# model params
+# for all class/function included in this repo, we use !<name> or !<new> for intialization, so that user may find all corresponding class/function according to one single yaml.
+# for system/third_party class/function, we do not require this.
+llm: !new:cosyvoice.llm.llm.CosyVoice3LM
+    llm_input_size: !ref <llm_input_size>
+    llm_output_size: !ref <llm_output_size>
+    speech_token_size: 6561
+    length_normalized_loss: True
+    lsm_weight: 0
+    mix_ratio: [5, 15]
+    llm: !new:cosyvoice.llm.llm.Qwen2Encoder
+        pretrain_path: !ref <qwen_pretrain_path>
+    sampling: !name:cosyvoice.utils.common.ras_sampling
+        top_p: 0.8
+        top_k: 25
+        win_size: 10
+        tau_r: 0.1
+
+flow: !new:cosyvoice.flow.flow.CausalMaskedDiffWithDiT
+    input_size: 80
+    output_size: 80
+    spk_embed_dim: !ref <spk_embed_dim>
+    output_type: 'mel'
+    vocab_size: 6561
+    input_frame_rate: !ref <token_frame_rate>
+    only_mask_loss: True
+    token_mel_ratio: !ref <token_mel_ratio>
+    pre_lookahead_len: 3
+    pre_lookahead_layer: !new:cosyvoice.transformer.upsample_encoder.PreLookaheadLayer
+        in_channels: 80
+        channels: 1024
+        pre_lookahead_len: 3
+    decoder: !new:cosyvoice.flow.flow_matching.CausalConditionalCFM
+        in_channels: 240
+        n_spks: 1
+        spk_emb_dim: 80
+        cfm_params: !new:omegaconf.DictConfig
+            content:
+                sigma_min: 1e-06
+                solver: 'euler'
+                t_scheduler: 'cosine'
+                training_cfg_rate: 0.2
+                inference_cfg_rate: 0.7
+                reg_loss_type: 'l1'
+        estimator: !new:cosyvoice.flow.DiT.dit.DiT
+            dim: 1024
+            depth: 22
+            heads: 16
+            dim_head: 64
+            ff_mult: 2
+            mel_dim: 80
+            mu_dim: 80
+            spk_dim: 80
+            out_channels: 80
+            static_chunk_size: !ref <chunk_size> * <token_mel_ratio>
+            num_decoding_left_chunks: !ref <num_decoding_left_chunks>
+
+hift: !new:cosyvoice.hifigan.generator.CausalHiFTGenerator
+    in_channels: 80
+    base_channels: 512
+    nb_harmonics: 8
+    sampling_rate: !ref <sample_rate>
+    nsf_alpha: 0.1
+    nsf_sigma: 0.003
+    nsf_voiced_threshold: 10
+    upsample_rates: [8, 5, 3]
+    upsample_kernel_sizes: [16, 11, 7]
+    istft_params:
+        n_fft: 16
+        hop_len: 4
+    resblock_kernel_sizes: [3, 7, 11]
+    resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+    source_resblock_kernel_sizes: [7, 7, 11]
+    source_resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+    lrelu_slope: 0.1
+    audio_limit: 0.99
+    conv_pre_look_right: 4
+    f0_predictor: !new:cosyvoice.hifigan.f0_predictor.CausalConvRNNF0Predictor
+        num_class: 1
+        in_channels: 80
+        cond_channels: 512
+
+# gan related module
+mel_spec_transform1: !name:matcha.utils.audio.mel_spectrogram
+    n_fft: 1920
+    num_mels: 80
+    sampling_rate: !ref <sample_rate>
+    hop_size: 480
+    win_size: 1920
+    fmin: 0
+    fmax: null
+    center: False
+hifigan: !new:cosyvoice.hifigan.hifigan.HiFiGan
+    generator: !ref <hift>
+    discriminator: !new:cosyvoice.hifigan.discriminator.MultipleDiscriminator
+        mpd: !new:matcha.hifigan.models.MultiPeriodDiscriminator
+        mrd: !new:cosyvoice.hifigan.discriminator.MultiResSpecDiscriminator
+    mel_spec_transform: [
+        !ref <mel_spec_transform1>
+    ]
+
+# processor functions
+parquet_opener: !name:cosyvoice.dataset.processor.parquet_opener
+get_tokenizer: !name:cosyvoice.tokenizer.tokenizer.get_qwen_tokenizer
+    token_path: !ref <qwen_pretrain_path>
+    skip_special_tokens: True
+    version: cosyvoice3
+allowed_special: 'all'
+tokenize: !name:cosyvoice.dataset.processor.tokenize
+    get_tokenizer: !ref <get_tokenizer>
+    allowed_special: !ref <allowed_special>
+filter: !name:cosyvoice.dataset.processor.filter
+    max_length: 40960
+    min_length: 100
+    token_max_length: 200
+    token_min_length: 1
+resample: !name:cosyvoice.dataset.processor.resample
+    resample_rate: !ref <sample_rate>
+truncate: !name:cosyvoice.dataset.processor.truncate
+    truncate_length: 24480 # must be a multiplier of hop_size
+feat_extractor: !name:matcha.utils.audio.mel_spectrogram
+    n_fft: 1920
+    num_mels: 80
+    sampling_rate: !ref <sample_rate>
+    hop_size: 480
+    win_size: 1920
+    fmin: 0
+    fmax: null
+    center: False
+compute_fbank: !name:cosyvoice.dataset.processor.compute_fbank
+    feat_extractor: !ref <feat_extractor>
+compute_f0: !name:cosyvoice.dataset.processor.compute_f0
+    sample_rate: !ref <sample_rate>
+    hop_size: 480
+parse_embedding: !name:cosyvoice.dataset.processor.parse_embedding
+    normalize: True
+shuffle: !name:cosyvoice.dataset.processor.shuffle
+    shuffle_size: 1000
+sort: !name:cosyvoice.dataset.processor.sort
+    sort_size: 500  # sort_size should be less than shuffle_size
+batch: !name:cosyvoice.dataset.processor.batch
+    batch_type: 'dynamic'
+    max_frames_in_batch: 2000
+padding: !name:cosyvoice.dataset.processor.padding
+    use_spk_embedding: False # change to True during sft
+
+
+# dataset processor pipeline
+data_pipeline: [
+    !ref <parquet_opener>,
+    !ref <tokenize>,
+    !ref <filter>,
+    !ref <resample>,
+    !ref <compute_fbank>,
+    !ref <parse_embedding>,
+    !ref <shuffle>,
+    !ref <sort>,
+    !ref <batch>,
+    !ref <padding>,
+]
+data_pipeline_gan: [
+    !ref <parquet_opener>,
+    !ref <tokenize>,
+    !ref <filter>,
+    !ref <resample>,
+    !ref <truncate>,
+    !ref <compute_fbank>,
+    !ref <compute_f0>,
+    !ref <parse_embedding>,
+    !ref <shuffle>,
+    !ref <sort>,
+    !ref <batch>,
+    !ref <padding>,
+]
+
+# llm flow train conf
+train_conf:
+    optim: adam
+    optim_conf:
+        lr: 1e-5 # change to 1e-5 during sft
+    scheduler: constantlr # change to constantlr during sft
+    scheduler_conf:
+        warmup_steps: 2500
+    max_epoch: 200
+    grad_clip: 5
+    accum_grad: 2
+    log_interval: 100
+    save_per_step: -1
+
+# gan train conf
+train_conf_gan:
+    optim: adam
+    optim_conf:
+        lr: 0.0002 # use small lr for gan training
+    scheduler: constantlr
+    optim_d: adam
+    optim_conf_d:
+        lr: 0.0002 # use small lr for gan training
+    scheduler_d: constantlr
+    max_epoch: 200
+    grad_clip: 5
+    accum_grad: 1 # in gan training, accum_grad must be 1
+    log_interval: 100
+    save_per_step: -1

flow.decoder.estimator.fp32.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b51b9533a55937762b262bf2cf9c6220ce40760f76d6532cb16a6a6d84059a8
+size 1326216933

flow.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6fab32a7825e5b0bc855ddd948f8db9370b0a786fbc249caa4595e95b608e4b
+size 1329116148

hift.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b279d7641eb97ae55b3b540cfba4f953c26492a2df758328a89a4d007ab87a65
+size 83202622

llm.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9565e41454e860768447f4ec5c5244a06b1ccdffdc7890fa593d907c93eebcc
+size 2024669130

speech_tokenizer_v3.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23236a74175dbdda47afc66dbadd5bcb41303c467a57c261cb8539ad9db9208d
+size 969451503