Upload model

CosyVoice-300M-25Hz/README.md

@@ -0,0 +1,169 @@
+# CosyVoice
+
+## 👉🏻 [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).
+
+## Install
+
+**Clone and install**
+
+- Clone the repo
+
+``` sh
+git clone --recursive https://github.com/FunAudioLLM/CosyVoice.git
+# If you failed to clone submodule due to network failures, please run 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 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
+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 `CosyVoice-300M` `CosyVoice-300M-SFT` `CosyVoice-300M-Instruct`
+model and `CosyVoice-ttsfrd` resource.
+
+If you are expert in this field, and you are only interested in training your own CosyVoice model from scratch, you can
+skip this step.
+
+``` python
+# SDK模型下载
+from modelscope import snapshot_download
+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')
+```
+
+``` sh
+# git模型下载，请确保已安装git lfs
+mkdir -p pretrained_models
+git clone https://www.modelscope.cn/iic/CosyVoice-300M.git pretrained_models/CosyVoice-300M
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-SFT.git pretrained_models/CosyVoice-300M-SFT
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-Instruct.git pretrained_models/CosyVoice-300M-Instruct
+git clone https://www.modelscope.cn/iic/CosyVoice-ttsfrd.git pretrained_models/CosyVoice-ttsfrd
+```
+
+Optionaly, you can unzip `ttsfrd` resouce 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 WeTextProcessing by default.
+
+``` sh
+cd pretrained_models/CosyVoice-ttsfrd/
+unzip resource.zip -d .
+pip install ttsfrd-0.3.6-cp38-cp38-linux_x86_64.whl
+```
+
+**Basic Usage**
+
+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.
+First, add `third_party/Matcha-TTS` to your `PYTHONPATH`.
+
+``` sh
+export PYTHONPATH=third_party/Matcha-TTS
+```
+
+``` python
+from cosyvoice.cli.cosyvoice import CosyVoice
+from cosyvoice.utils.file_utils import load_wav
+import torchaudio
+
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT')
+# sft usage
+print(cosyvoice.list_avaliable_spks())
+# change stream=True for chunk stream inference
+for i, j in enumerate(cosyvoice.inference_sft('你好，我是通义生成式语音大模型，请问有什么可以帮您的吗？', '中文女', stream=False)):
+    torchaudio.save('sft_{}.wav'.format(i), j['tts_speech'], 22050)
+
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M')
+# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
+prompt_speech_16k = load_wav('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'], 22050)
+# cross_lingual usage
+prompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
+for i, j in enumerate(cosyvoice.inference_cross_lingual('<|en|>And then later on, fully acquiring that company. So keeping management in line, interest in line with the asset that\'s coming into the family is a reason why sometimes we don\'t buy the whole thing.', prompt_speech_16k, stream=False)):
+    torchaudio.save('cross_lingual_{}.wav'.format(i), j['tts_speech'], 22050)
+
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-Instruct')
+# instruct usage, support <laughter></laughter><strong></strong>[laughter][breath]
+for i, j in enumerate(cosyvoice.inference_instruct('在面对挑战时，他展现了非凡的<strong>勇气</strong>与<strong>智慧</strong>。', '中文男', 'Theo \'Crimson\', is a fiery, passionate rebel leader. Fights with fervor for justice, but struggles with impulsiveness.', stream=False)):
+    torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], 22050)
+```
+
+**Start web demo**
+
+You can use our web demo page to get familiar with CosyVoice quickly.
+We support sft/zero_shot/cross_lingual/instruct inference in web demo.
+
+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 user, we have provided train and inference scripts in `examples/libritts/cosyvoice/run.sh`.
+You can get familiar with CosyVoice following this recipie.
+
+**Build for deployment**
+
+Optionally, if you want to use grpc for service deployment,
+you can run following steps. Otherwise, you can just ignore this step.
+
+``` 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 && MODEL_DIR=iic/CosyVoice-300M fastapi dev --port 50000 server.py && sleep infinity"
+cd fastapi && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>
+```
+
+## 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).
+
+## 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-300M-25Hz/campplus.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ac6a63997761ae2997373e2ee1c47040854b4b759ea41ec48e4e42df0f4d73
+size 28303423

CosyVoice-300M-25Hz/configuration.json

@@ -0,0 +1,4 @@
+{
+    "framework": "Pytorch",
+    "task": "text-to-speech"
+}

CosyVoice-300M-25Hz/cosyvoice.yaml

@@ -0,0 +1,203 @@
+# 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: 22050
+text_encoder_input_size: 512
+llm_input_size: 1024
+llm_output_size: 1024
+spk_embed_dim: 192
+
+# 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.TransformerLM
+    text_encoder_input_size: !ref <text_encoder_input_size>
+    llm_input_size: !ref <llm_input_size>
+    llm_output_size: !ref <llm_output_size>
+    text_token_size: 60515 # change to 60515 if you want to train with CosyVoice-300M-25Hz recipe
+    speech_token_size: 4096
+    length_normalized_loss: True
+    lsm_weight: 0
+    spk_embed_dim: !ref <spk_embed_dim>
+    text_encoder: !new:cosyvoice.transformer.encoder.ConformerEncoder
+        input_size: !ref <text_encoder_input_size>
+        output_size: 1024
+        attention_heads: 16
+        linear_units: 4096
+        num_blocks: 6
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.0
+        normalize_before: True
+        input_layer: "linear"
+        pos_enc_layer_type: "rel_pos_espnet"
+        selfattention_layer_type: "rel_selfattn"
+        use_cnn_module: False
+        macaron_style: False
+        use_dynamic_chunk: False
+        use_dynamic_left_chunk: False
+        static_chunk_size: 1
+    llm: !new:cosyvoice.transformer.encoder.TransformerEncoder
+        input_size: !ref <llm_input_size>
+        output_size: !ref <llm_output_size>
+        attention_heads: 16
+        linear_units: 4096
+        num_blocks: 14
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.0
+        input_layer: "linear_legacy"
+        pos_enc_layer_type: "rel_pos_espnet"
+        selfattention_layer_type: "rel_selfattn"
+        static_chunk_size: 1
+    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.MaskedDiffWithXvec
+    input_size: 512
+    output_size: 80
+    spk_embed_dim: !ref <spk_embed_dim>
+    output_type: "mel"
+    vocab_size: 4096
+    input_frame_rate: 25 # change to 25 if you want to train with CosyVoice-300M-25Hz recipe
+    only_mask_loss: True
+    encoder: !new:cosyvoice.transformer.encoder.ConformerEncoder
+        output_size: 512
+        attention_heads: 8
+        linear_units: 2048
+        num_blocks: 6
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.1
+        normalize_before: True
+        input_layer: "linear"
+        pos_enc_layer_type: "rel_pos_espnet"
+        selfattention_layer_type: "rel_selfattn"
+        input_size: 512
+        use_cnn_module: False
+        macaron_style: False
+    length_regulator: !new:cosyvoice.flow.length_regulator.InterpolateRegulator
+        channels: 80
+        sampling_ratios: [1, 1, 1, 1]
+    decoder: !new:cosyvoice.flow.flow_matching.ConditionalCFM
+        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.decoder.ConditionalDecoder
+            in_channels: 320
+            out_channels: 80
+            channels: [256, 256]
+            dropout: 0.0
+            attention_head_dim: 64
+            n_blocks: 4
+            num_mid_blocks: 12
+            num_heads: 8
+            act_fn: "gelu"
+
+hift: !new:cosyvoice.hifigan.generator.HiFTGenerator
+    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, 8]
+    upsample_kernel_sizes: [16, 16]
+    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, 11]
+    source_resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5]]
+    lrelu_slope: 0.1
+    audio_limit: 0.99
+    f0_predictor: !new:cosyvoice.hifigan.f0_predictor.ConvRNNF0Predictor
+        num_class: 1
+        in_channels: 80
+        cond_channels: 512
+
+# processor functions
+parquet_opener: !name:cosyvoice.dataset.processor.parquet_opener
+get_tokenizer: !name:cosyvoice.tokenizer.tokenizer.get_tokenizer
+    multilingual: True
+    num_languages: 100
+    language: "en"
+    task: "transcribe"
+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: 0
+    token_max_length: 200
+    token_min_length: 1
+resample: !name:cosyvoice.dataset.processor.resample
+    resample_rate: !ref <sample_rate>
+feat_extractor: !name:cosyvoice.utils.audio.mel_spectrogram
+    n_fft: 1024
+    num_mels: 80
+    sampling_rate: !ref <sample_rate>
+    hop_size: 256
+    win_size: 1024
+    fmin: 0
+    fmax: 8000
+    center: False
+compute_fbank: !name:cosyvoice.dataset.processor.compute_fbank
+    feat_extractor: !ref <feat_extractor>
+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 # 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>,
+    ]
+
+# train conf
+train_conf:
+    optim: adam
+    optim_conf:
+        lr: 1e-5 # change to 1e-5 during sft
+    scheduler: warmuplr # 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

CosyVoice-300M-25Hz/flow.decoder.estimator.fp32.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37e81b4ab4c0c66d7c68fbe56da62b246c56254ecb72d8e9afd2770b8e34020
+size 328627300

CosyVoice-300M-25Hz/flow.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1411de192039a21d53f0bf1968feb50586ce71d81ea1443f8163f4d1c46c5455
+size 419901370

CosyVoice-300M-25Hz/hift.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e679b6ca1eff71187ffb4f3ab0444935594cdcc20a9bd12afad111ef8d6012
+size 81896716

CosyVoice-300M-25Hz/llm.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23bc18a6d53b516868c7827fdedfd86df16642913e168ed6949fe07464c7d6ae
+size 1260708412

CosyVoice-300M-25Hz/speech_tokenizer_v1.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56285ddd4a83e883ee0cb9f8d69c1089b53a94b1f78ff7e4a0224a27eb4cb486
+size 522625011

CosyVoice-300M-25Hz/spk2info.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b1d62ca87cdcb25a9003fa0c8f2cba5c94f55b0d5f80f0b63ef8c22d919cfc
+size 7772

CosyVoice-300M-Instruct/README.md

@@ -0,0 +1,227 @@
+[![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://arxiv.org/abs/2412.10117); [Modelscope](https://www.modelscope.cn/studios/iic/CosyVoice2-0.5B); [HuggingFace](https://huggingface.co/spaces/FunAudioLLM/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
+- **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.
+
+## Roadmap
+
+- [x] 2024/12
+
+    - [x] 25hz cosyvoice 2.0 released
+
+- [x] 2024/09
+
+    - [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] 2024/07
+
+    - [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 submodule due to network failures, please run 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 python=3.10
+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
+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
+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-25Hz', local_dir='pretrained_models/CosyVoice-300M-25Hz')
+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')
+```
+
+``` sh
+# git模型下载，请确保已安装git lfs
+mkdir -p pretrained_models
+git clone https://www.modelscope.cn/iic/CosyVoice2-0.5B.git pretrained_models/CosyVoice2-0.5B
+git clone https://www.modelscope.cn/iic/CosyVoice-300M.git pretrained_models/CosyVoice-300M
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-25Hz.git pretrained_models/CosyVoice-300M-25Hz
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-SFT.git pretrained_models/CosyVoice-300M-SFT
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-Instruct.git pretrained_models/CosyVoice-300M-Instruct
+git clone https://www.modelscope.cn/iic/CosyVoice-ttsfrd.git pretrained_models/CosyVoice-ttsfrd
+```
+
+Optionally, you can unzip `ttsfrd` resouce 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 WeTextProcessing 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 `CosyVoice2-0.5B` for better performance.
+Follow code below for detailed usage of each model.
+
+``` python
+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
+```
+
+**CosyVoice2 Usage**
+```python
+cosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=False, load_trt=False, fp16=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('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)
+
+# 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)
+```
+
+**CosyVoice Usage**
+```python
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=False, load_trt=False, fp16=False)
+# sft usage
+print(cosyvoice.list_available_spks())
+# change stream=True for chunk stream inference
+for i, j in enumerate(cosyvoice.inference_sft('你好，我是通义生成式语音大模型，请问有什么可以帮您的吗？', '中文女', stream=False)):
+    torchaudio.save('sft_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M') # or change to pretrained_models/CosyVoice-300M-25Hz for 25Hz inference
+# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
+prompt_speech_16k = load_wav('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)
+# cross_lingual usage
+prompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
+for i, j in enumerate(cosyvoice.inference_cross_lingual('<|en|>And then later on, fully acquiring that company. So keeping management in line, interest in line with the asset that\'s coming into the family is a reason why sometimes we don\'t buy the whole thing.', prompt_speech_16k, stream=False)):
+    torchaudio.save('cross_lingual_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+# vc usage
+prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
+source_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
+for i, j in enumerate(cosyvoice.inference_vc(source_speech_16k, prompt_speech_16k, stream=False)):
+    torchaudio.save('vc_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-Instruct')
+# instruct usage, support <laughter></laughter><strong></strong>[laughter][breath]
+for i, j in enumerate(cosyvoice.inference_instruct('在面对挑战时，他展现了非凡的<strong>勇气</strong>与<strong>智慧</strong>。', '中文男', 'Theo \'Crimson\', is a fiery, passionate rebel leader. Fights with fervor for justice, but struggles with impulsiveness.', stream=False)):
+    torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+```
+
+**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 user, we have provided train and inference scripts in `examples/libritts/cosyvoice/run.sh`.
+
+**Build for deployment**
+
+Optionally, if you want service deployment,
+you can run 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>
+```
+
+## 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).
+
+## 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-300M-Instruct/campplus.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ac6a63997761ae2997373e2ee1c47040854b4b759ea41ec48e4e42df0f4d73
+size 28303423

CosyVoice-300M-Instruct/configuration.json

@@ -0,0 +1,4 @@
+{
+    "framework": "Pytorch",
+    "task": "text-to-speech"
+}

CosyVoice-300M-Instruct/cosyvoice.yaml

@@ -0,0 +1,203 @@
+# 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: 22050
+text_encoder_input_size: 512
+llm_input_size: 1024
+llm_output_size: 1024
+spk_embed_dim: 192
+
+# 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.TransformerLM
+    text_encoder_input_size: !ref <text_encoder_input_size>
+    llm_input_size: !ref <llm_input_size>
+    llm_output_size: !ref <llm_output_size>
+    text_token_size: 51866 # change to 60515 if you want to train with CosyVoice-300M-25Hz recipe
+    speech_token_size: 4096
+    length_normalized_loss: True
+    lsm_weight: 0
+    spk_embed_dim: !ref <spk_embed_dim>
+    text_encoder: !new:cosyvoice.transformer.encoder.ConformerEncoder
+        input_size: !ref <text_encoder_input_size>
+        output_size: 1024
+        attention_heads: 16
+        linear_units: 4096
+        num_blocks: 6
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.0
+        normalize_before: True
+        input_layer: "linear"
+        pos_enc_layer_type: "rel_pos_espnet"
+        selfattention_layer_type: "rel_selfattn"
+        use_cnn_module: False
+        macaron_style: False
+        use_dynamic_chunk: False
+        use_dynamic_left_chunk: False
+        static_chunk_size: 1
+    llm: !new:cosyvoice.transformer.encoder.TransformerEncoder
+        input_size: !ref <llm_input_size>
+        output_size: !ref <llm_output_size>
+        attention_heads: 16
+        linear_units: 4096
+        num_blocks: 14
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.0
+        input_layer: "linear_legacy"
+        pos_enc_layer_type: "rel_pos_espnet"
+        selfattention_layer_type: "rel_selfattn"
+        static_chunk_size: 1
+    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.MaskedDiffWithXvec
+    input_size: 512
+    output_size: 80
+    spk_embed_dim: !ref <spk_embed_dim>
+    output_type: "mel"
+    vocab_size: 4096
+    input_frame_rate: 50 # change to 25 if you want to train with CosyVoice-300M-25Hz recipe
+    only_mask_loss: True
+    encoder: !new:cosyvoice.transformer.encoder.ConformerEncoder
+        output_size: 512
+        attention_heads: 8
+        linear_units: 2048
+        num_blocks: 6
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.1
+        normalize_before: True
+        input_layer: "linear"
+        pos_enc_layer_type: "rel_pos_espnet"
+        selfattention_layer_type: "rel_selfattn"
+        input_size: 512
+        use_cnn_module: False
+        macaron_style: False
+    length_regulator: !new:cosyvoice.flow.length_regulator.InterpolateRegulator
+        channels: 80
+        sampling_ratios: [1, 1, 1, 1]
+    decoder: !new:cosyvoice.flow.flow_matching.ConditionalCFM
+        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.decoder.ConditionalDecoder
+            in_channels: 320
+            out_channels: 80
+            channels: [256, 256]
+            dropout: 0.0
+            attention_head_dim: 64
+            n_blocks: 4
+            num_mid_blocks: 12
+            num_heads: 8
+            act_fn: "gelu"
+
+hift: !new:cosyvoice.hifigan.generator.HiFTGenerator
+    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, 8]
+    upsample_kernel_sizes: [16, 16]
+    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, 11]
+    source_resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5]]
+    lrelu_slope: 0.1
+    audio_limit: 0.99
+    f0_predictor: !new:cosyvoice.hifigan.f0_predictor.ConvRNNF0Predictor
+        num_class: 1
+        in_channels: 80
+        cond_channels: 512
+
+# processor functions
+parquet_opener: !name:cosyvoice.dataset.processor.parquet_opener
+get_tokenizer: !name:cosyvoice.tokenizer.tokenizer.get_tokenizer
+    multilingual: True
+    num_languages: 100
+    language: "en"
+    task: "transcribe"
+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: 0
+    token_max_length: 200
+    token_min_length: 1
+resample: !name:cosyvoice.dataset.processor.resample
+    resample_rate: !ref <sample_rate>
+feat_extractor: !name:cosyvoice.utils.audio.mel_spectrogram
+    n_fft: 1024
+    num_mels: 80
+    sampling_rate: !ref <sample_rate>
+    hop_size: 256
+    win_size: 1024
+    fmin: 0
+    fmax: 8000
+    center: False
+compute_fbank: !name:cosyvoice.dataset.processor.compute_fbank
+    feat_extractor: !ref <feat_extractor>
+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 # 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>,
+    ]
+
+# train conf
+train_conf:
+    optim: adam
+    optim_conf:
+        lr: 0.001 # change to 1e-5 during sft
+    scheduler: warmuplr # 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

CosyVoice-300M-Instruct/hift.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e679b6ca1eff71187ffb4f3ab0444935594cdcc20a9bd12afad111ef8d6012
+size 81896716

CosyVoice-300M-SFT/README.md

@@ -0,0 +1,227 @@
+[![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://arxiv.org/abs/2412.10117); [Modelscope](https://www.modelscope.cn/studios/iic/CosyVoice2-0.5B); [HuggingFace](https://huggingface.co/spaces/FunAudioLLM/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
+- **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.
+
+## Roadmap
+
+- [x] 2024/12
+
+    - [x] 25hz cosyvoice 2.0 released
+
+- [x] 2024/09
+
+    - [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] 2024/07
+
+    - [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 submodule due to network failures, please run 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 python=3.10
+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
+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
+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-25Hz', local_dir='pretrained_models/CosyVoice-300M-25Hz')
+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')
+```
+
+``` sh
+# git模型下载，请确保已安装git lfs
+mkdir -p pretrained_models
+git clone https://www.modelscope.cn/iic/CosyVoice2-0.5B.git pretrained_models/CosyVoice2-0.5B
+git clone https://www.modelscope.cn/iic/CosyVoice-300M.git pretrained_models/CosyVoice-300M
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-25Hz.git pretrained_models/CosyVoice-300M-25Hz
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-SFT.git pretrained_models/CosyVoice-300M-SFT
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-Instruct.git pretrained_models/CosyVoice-300M-Instruct
+git clone https://www.modelscope.cn/iic/CosyVoice-ttsfrd.git pretrained_models/CosyVoice-ttsfrd
+```
+
+Optionally, you can unzip `ttsfrd` resouce 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 WeTextProcessing 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 `CosyVoice2-0.5B` for better performance.
+Follow code below for detailed usage of each model.
+
+``` python
+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
+```
+
+**CosyVoice2 Usage**
+```python
+cosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=False, load_trt=False, fp16=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('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)
+
+# 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)
+```
+
+**CosyVoice Usage**
+```python
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=False, load_trt=False, fp16=False)
+# sft usage
+print(cosyvoice.list_available_spks())
+# change stream=True for chunk stream inference
+for i, j in enumerate(cosyvoice.inference_sft('你好，我是通义生成式语音大模型，请问有什么可以帮您的吗？', '中文女', stream=False)):
+    torchaudio.save('sft_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M') # or change to pretrained_models/CosyVoice-300M-25Hz for 25Hz inference
+# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
+prompt_speech_16k = load_wav('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)
+# cross_lingual usage
+prompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
+for i, j in enumerate(cosyvoice.inference_cross_lingual('<|en|>And then later on, fully acquiring that company. So keeping management in line, interest in line with the asset that\'s coming into the family is a reason why sometimes we don\'t buy the whole thing.', prompt_speech_16k, stream=False)):
+    torchaudio.save('cross_lingual_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+# vc usage
+prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
+source_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
+for i, j in enumerate(cosyvoice.inference_vc(source_speech_16k, prompt_speech_16k, stream=False)):
+    torchaudio.save('vc_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-Instruct')
+# instruct usage, support <laughter></laughter><strong></strong>[laughter][breath]
+for i, j in enumerate(cosyvoice.inference_instruct('在面对挑战时，他展现了非凡的<strong>勇气</strong>与<strong>智慧</strong>。', '中文男', 'Theo \'Crimson\', is a fiery, passionate rebel leader. Fights with fervor for justice, but struggles with impulsiveness.', stream=False)):
+    torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+```
+
+**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 user, we have provided train and inference scripts in `examples/libritts/cosyvoice/run.sh`.
+
+**Build for deployment**
+
+Optionally, if you want service deployment,
+you can run 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>
+```
+
+## 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).
+
+## 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-300M-SFT/campplus.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ac6a63997761ae2997373e2ee1c47040854b4b759ea41ec48e4e42df0f4d73
+size 28303423

CosyVoice-300M-SFT/configuration.json

@@ -0,0 +1,4 @@
+{
+    "framework": "Pytorch",
+    "task": "text-to-speech"
+}

CosyVoice-300M-SFT/cosyvoice.yaml

@@ -0,0 +1,203 @@
+# 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: 22050
+text_encoder_input_size: 512
+llm_input_size: 1024
+llm_output_size: 1024
+spk_embed_dim: 192
+
+# 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.TransformerLM
+    text_encoder_input_size: !ref <text_encoder_input_size>
+    llm_input_size: !ref <llm_input_size>
+    llm_output_size: !ref <llm_output_size>
+    text_token_size: 51866 # change to 60515 if you want to train with CosyVoice-300M-25Hz recipe
+    speech_token_size: 4096
+    length_normalized_loss: True
+    lsm_weight: 0
+    spk_embed_dim: !ref <spk_embed_dim>
+    text_encoder: !new:cosyvoice.transformer.encoder.ConformerEncoder
+        input_size: !ref <text_encoder_input_size>
+        output_size: 1024
+        attention_heads: 16
+        linear_units: 4096
+        num_blocks: 6
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.0
+        normalize_before: True
+        input_layer: "linear"
+        pos_enc_layer_type: "rel_pos_espnet"
+        selfattention_layer_type: "rel_selfattn"
+        use_cnn_module: False
+        macaron_style: False
+        use_dynamic_chunk: False
+        use_dynamic_left_chunk: False
+        static_chunk_size: 1
+    llm: !new:cosyvoice.transformer.encoder.TransformerEncoder
+        input_size: !ref <llm_input_size>
+        output_size: !ref <llm_output_size>
+        attention_heads: 16
+        linear_units: 4096
+        num_blocks: 14
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.0
+        input_layer: "linear_legacy"
+        pos_enc_layer_type: "rel_pos_espnet"
+        selfattention_layer_type: "rel_selfattn"
+        static_chunk_size: 1
+    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.MaskedDiffWithXvec
+    input_size: 512
+    output_size: 80
+    spk_embed_dim: !ref <spk_embed_dim>
+    output_type: "mel"
+    vocab_size: 4096
+    input_frame_rate: 50 # change to 25 if you want to train with CosyVoice-300M-25Hz recipe
+    only_mask_loss: True
+    encoder: !new:cosyvoice.transformer.encoder.ConformerEncoder
+        output_size: 512
+        attention_heads: 8
+        linear_units: 2048
+        num_blocks: 6
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.1
+        normalize_before: True
+        input_layer: "linear"
+        pos_enc_layer_type: "rel_pos_espnet"
+        selfattention_layer_type: "rel_selfattn"
+        input_size: 512
+        use_cnn_module: False
+        macaron_style: False
+    length_regulator: !new:cosyvoice.flow.length_regulator.InterpolateRegulator
+        channels: 80
+        sampling_ratios: [1, 1, 1, 1]
+    decoder: !new:cosyvoice.flow.flow_matching.ConditionalCFM
+        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.decoder.ConditionalDecoder
+            in_channels: 320
+            out_channels: 80
+            channels: [256, 256]
+            dropout: 0.0
+            attention_head_dim: 64
+            n_blocks: 4
+            num_mid_blocks: 12
+            num_heads: 8
+            act_fn: "gelu"
+
+hift: !new:cosyvoice.hifigan.generator.HiFTGenerator
+    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, 8]
+    upsample_kernel_sizes: [16, 16]
+    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, 11]
+    source_resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5]]
+    lrelu_slope: 0.1
+    audio_limit: 0.99
+    f0_predictor: !new:cosyvoice.hifigan.f0_predictor.ConvRNNF0Predictor
+        num_class: 1
+        in_channels: 80
+        cond_channels: 512
+
+# processor functions
+parquet_opener: !name:cosyvoice.dataset.processor.parquet_opener
+get_tokenizer: !name:cosyvoice.tokenizer.tokenizer.get_tokenizer
+    multilingual: True
+    num_languages: 100
+    language: "en"
+    task: "transcribe"
+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: 0
+    token_max_length: 200
+    token_min_length: 1
+resample: !name:cosyvoice.dataset.processor.resample
+    resample_rate: !ref <sample_rate>
+feat_extractor: !name:cosyvoice.utils.audio.mel_spectrogram
+    n_fft: 1024
+    num_mels: 80
+    sampling_rate: !ref <sample_rate>
+    hop_size: 256
+    win_size: 1024
+    fmin: 0
+    fmax: 8000
+    center: False
+compute_fbank: !name:cosyvoice.dataset.processor.compute_fbank
+    feat_extractor: !ref <feat_extractor>
+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 # 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>,
+    ]
+
+# train conf
+train_conf:
+    optim: adam
+    optim_conf:
+        lr: 0.001 # change to 1e-5 during sft
+    scheduler: warmuplr # 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

CosyVoice-300M-SFT/flow.decoder.estimator.fp32.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b71b58497f56a5b5e8f2cacc8c2c5088b0fb0e8f9547e1a39269f0a98d0c92
+size 328698885

CosyVoice-300M-SFT/flow.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21eae78c105b5e1c6c337b04f667843377651b4bcfb2d43247ed3ad7fd0a3470
+size 419900943

CosyVoice-300M-SFT/hift.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e679b6ca1eff71187ffb4f3ab0444935594cdcc20a9bd12afad111ef8d6012
+size 81896716

CosyVoice-300M-SFT/llm.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d198ce56636e1eb1c9d0cb0d6e3529de8fdfd3fd45075c346296b0d6dcfc54ea
+size 1242994835

CosyVoice-300M-SFT/speech_tokenizer_v1.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b5a723ed9143aebfd9ffda14ac4c21231f31c35ef837b6a13bb9e5488abb1e
+size 522624269

CosyVoice-300M-SFT/spk2info.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b1d62ca87cdcb25a9003fa0c8f2cba5c94f55b0d5f80f0b63ef8c22d919cfc
+size 7772

CosyVoice-300M/README.md

@@ -0,0 +1,227 @@
+[![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://arxiv.org/abs/2412.10117); [Modelscope](https://www.modelscope.cn/studios/iic/CosyVoice2-0.5B); [HuggingFace](https://huggingface.co/spaces/FunAudioLLM/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
+- **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.
+
+## Roadmap
+
+- [x] 2024/12
+
+    - [x] 25hz cosyvoice 2.0 released
+
+- [x] 2024/09
+
+    - [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] 2024/07
+
+    - [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 submodule due to network failures, please run 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 python=3.10
+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
+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
+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-25Hz', local_dir='pretrained_models/CosyVoice-300M-25Hz')
+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')
+```
+
+``` sh
+# git模型下载，请确保已安装git lfs
+mkdir -p pretrained_models
+git clone https://www.modelscope.cn/iic/CosyVoice2-0.5B.git pretrained_models/CosyVoice2-0.5B
+git clone https://www.modelscope.cn/iic/CosyVoice-300M.git pretrained_models/CosyVoice-300M
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-25Hz.git pretrained_models/CosyVoice-300M-25Hz
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-SFT.git pretrained_models/CosyVoice-300M-SFT
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-Instruct.git pretrained_models/CosyVoice-300M-Instruct
+git clone https://www.modelscope.cn/iic/CosyVoice-ttsfrd.git pretrained_models/CosyVoice-ttsfrd
+```
+
+Optionally, you can unzip `ttsfrd` resouce 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 WeTextProcessing 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 `CosyVoice2-0.5B` for better performance.
+Follow code below for detailed usage of each model.
+
+``` python
+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
+```
+
+**CosyVoice2 Usage**
+```python
+cosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=False, load_trt=False, fp16=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('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)
+
+# 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)
+```
+
+**CosyVoice Usage**
+```python
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=False, load_trt=False, fp16=False)
+# sft usage
+print(cosyvoice.list_available_spks())
+# change stream=True for chunk stream inference
+for i, j in enumerate(cosyvoice.inference_sft('你好，我是通义生成式语音大模型，请问有什么可以帮您的吗？', '中文女', stream=False)):
+    torchaudio.save('sft_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M') # or change to pretrained_models/CosyVoice-300M-25Hz for 25Hz inference
+# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
+prompt_speech_16k = load_wav('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)
+# cross_lingual usage
+prompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
+for i, j in enumerate(cosyvoice.inference_cross_lingual('<|en|>And then later on, fully acquiring that company. So keeping management in line, interest in line with the asset that\'s coming into the family is a reason why sometimes we don\'t buy the whole thing.', prompt_speech_16k, stream=False)):
+    torchaudio.save('cross_lingual_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+# vc usage
+prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
+source_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
+for i, j in enumerate(cosyvoice.inference_vc(source_speech_16k, prompt_speech_16k, stream=False)):
+    torchaudio.save('vc_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-Instruct')
+# instruct usage, support <laughter></laughter><strong></strong>[laughter][breath]
+for i, j in enumerate(cosyvoice.inference_instruct('在面对挑战时，他展现了非凡的<strong>勇气</strong>与<strong>智慧</strong>。', '中文男', 'Theo \'Crimson\', is a fiery, passionate rebel leader. Fights with fervor for justice, but struggles with impulsiveness.', stream=False)):
+    torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+```
+
+**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 user, we have provided train and inference scripts in `examples/libritts/cosyvoice/run.sh`.
+
+**Build for deployment**
+
+Optionally, if you want service deployment,
+you can run 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>
+```
+
+## 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).
+
+## 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-300M/campplus.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ac6a63997761ae2997373e2ee1c47040854b4b759ea41ec48e4e42df0f4d73
+size 28303423

CosyVoice-300M/configuration.json

@@ -0,0 +1,4 @@
+{
+    "framework": "Pytorch",
+    "task": "text-to-speech"
+}

CosyVoice-300M/cosyvoice.yaml

@@ -0,0 +1,203 @@
+# 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: 22050
+text_encoder_input_size: 512
+llm_input_size: 1024
+llm_output_size: 1024
+spk_embed_dim: 192
+
+# 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.TransformerLM
+    text_encoder_input_size: !ref <text_encoder_input_size>
+    llm_input_size: !ref <llm_input_size>
+    llm_output_size: !ref <llm_output_size>
+    text_token_size: 51866 # change to 60515 if you want to train with CosyVoice-300M-25Hz recipe
+    speech_token_size: 4096
+    length_normalized_loss: True
+    lsm_weight: 0
+    spk_embed_dim: !ref <spk_embed_dim>
+    text_encoder: !new:cosyvoice.transformer.encoder.ConformerEncoder
+        input_size: !ref <text_encoder_input_size>
+        output_size: 1024
+        attention_heads: 16
+        linear_units: 4096
+        num_blocks: 6
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.0
+        normalize_before: True
+        input_layer: "linear"
+        pos_enc_layer_type: "rel_pos_espnet"
+        selfattention_layer_type: "rel_selfattn"
+        use_cnn_module: False
+        macaron_style: False
+        use_dynamic_chunk: False
+        use_dynamic_left_chunk: False
+        static_chunk_size: 1
+    llm: !new:cosyvoice.transformer.encoder.TransformerEncoder
+        input_size: !ref <llm_input_size>
+        output_size: !ref <llm_output_size>
+        attention_heads: 16
+        linear_units: 4096
+        num_blocks: 14
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.0
+        input_layer: "linear_legacy"
+        pos_enc_layer_type: "rel_pos_espnet"
+        selfattention_layer_type: "rel_selfattn"
+        static_chunk_size: 1
+    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.MaskedDiffWithXvec
+    input_size: 512
+    output_size: 80
+    spk_embed_dim: !ref <spk_embed_dim>
+    output_type: "mel"
+    vocab_size: 4096
+    input_frame_rate: 50 # change to 25 if you want to train with CosyVoice-300M-25Hz recipe
+    only_mask_loss: True
+    encoder: !new:cosyvoice.transformer.encoder.ConformerEncoder
+        output_size: 512
+        attention_heads: 8
+        linear_units: 2048
+        num_blocks: 6
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.1
+        normalize_before: True
+        input_layer: "linear"
+        pos_enc_layer_type: "rel_pos_espnet"
+        selfattention_layer_type: "rel_selfattn"
+        input_size: 512
+        use_cnn_module: False
+        macaron_style: False
+    length_regulator: !new:cosyvoice.flow.length_regulator.InterpolateRegulator
+        channels: 80
+        sampling_ratios: [1, 1, 1, 1]
+    decoder: !new:cosyvoice.flow.flow_matching.ConditionalCFM
+        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.decoder.ConditionalDecoder
+            in_channels: 320
+            out_channels: 80
+            channels: [256, 256]
+            dropout: 0.0
+            attention_head_dim: 64
+            n_blocks: 4
+            num_mid_blocks: 12
+            num_heads: 8
+            act_fn: "gelu"
+
+hift: !new:cosyvoice.hifigan.generator.HiFTGenerator
+    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, 8]
+    upsample_kernel_sizes: [16, 16]
+    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, 11]
+    source_resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5]]
+    lrelu_slope: 0.1
+    audio_limit: 0.99
+    f0_predictor: !new:cosyvoice.hifigan.f0_predictor.ConvRNNF0Predictor
+        num_class: 1
+        in_channels: 80
+        cond_channels: 512
+
+# processor functions
+parquet_opener: !name:core.cosyvoice.dataset.processor.parquet_opener
+get_tokenizer: !name:core.cosyvoice.tokenizer.tokenizer.get_tokenizer
+    multilingual: True
+    num_languages: 100
+    language: "en"
+    task: "transcribe"
+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: 0
+    token_max_length: 200
+    token_min_length: 1
+resample: !name:cosyvoice.dataset.processor.resample
+    resample_rate: !ref <sample_rate>
+feat_extractor: !name:cosyvoice.utils.audio.mel_spectrogram
+    n_fft: 1024
+    num_mels: 80
+    sampling_rate: !ref <sample_rate>
+    hop_size: 256
+    win_size: 1024
+    fmin: 0
+    fmax: 8000
+    center: False
+compute_fbank: !name:cosyvoice.dataset.processor.compute_fbank
+    feat_extractor: !ref <feat_extractor>
+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 # 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>,
+    ]
+
+# train conf
+train_conf:
+    optim: adam
+    optim_conf:
+        lr: 0.001 # change to 1e-5 during sft
+    scheduler: warmuplr # 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

CosyVoice-300M/flow.decoder.estimator.fp32.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c02bc651f599d66e5786b9dc66d7841153a2f1ae682306a5bac84d067f7c947
+size 328698885

CosyVoice-300M/flow.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd80b089444a95e52956c57cdf177d7f6017a5af13b8a697717628a1d2be6b55
+size 419900943

CosyVoice-300M/hift.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e679b6ca1eff71187ffb4f3ab0444935594cdcc20a9bd12afad111ef8d6012
+size 81896716

CosyVoice-300M/llm.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f7eb172d2f33f6c8c02709d829c83960f97876fa9886c7ea232597b51af976
+size 1242994835

CosyVoice-300M/speech_tokenizer_v1.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b5a723ed9143aebfd9ffda14ac4c21231f31c35ef837b6a13bb9e5488abb1e
+size 522624269

CosyVoice2-0.5B/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
+}

CosyVoice2-0.5B/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"
+}

CosyVoice2-0.5B/CosyVoice-BlankEN/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130282af0dfa9fe5840737cc49a0d339d06075f83c5a315c3372c9a0740d0b96
+size 988097824

CosyVoice2-0.5B/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
+}

CosyVoice2-0.5B/README.md

@@ -0,0 +1,227 @@
+[![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://arxiv.org/abs/2412.10117); [Modelscope](https://www.modelscope.cn/studios/iic/CosyVoice2-0.5B); [HuggingFace](https://huggingface.co/spaces/FunAudioLLM/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
+- **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.
+
+## Roadmap
+
+- [x] 2024/12
+
+    - [x] 25hz cosyvoice 2.0 released
+
+- [x] 2024/09
+
+    - [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] 2024/07
+
+    - [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 submodule due to network failures, please run 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 python=3.10
+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
+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
+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-25Hz', local_dir='pretrained_models/CosyVoice-300M-25Hz')
+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')
+```
+
+``` sh
+# git模型下载，请确保已安装git lfs
+mkdir -p pretrained_models
+git clone https://www.modelscope.cn/iic/CosyVoice2-0.5B.git pretrained_models/CosyVoice2-0.5B
+git clone https://www.modelscope.cn/iic/CosyVoice-300M.git pretrained_models/CosyVoice-300M
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-25Hz.git pretrained_models/CosyVoice-300M-25Hz
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-SFT.git pretrained_models/CosyVoice-300M-SFT
+git clone https://www.modelscope.cn/iic/CosyVoice-300M-Instruct.git pretrained_models/CosyVoice-300M-Instruct
+git clone https://www.modelscope.cn/iic/CosyVoice-ttsfrd.git pretrained_models/CosyVoice-ttsfrd
+```
+
+Optionally, you can unzip `ttsfrd` resouce 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 WeTextProcessing 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 `CosyVoice2-0.5B` for better performance.
+Follow code below for detailed usage of each model.
+
+``` python
+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
+```
+
+**CosyVoice2 Usage**
+```python
+cosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=False, load_trt=False, fp16=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('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)
+
+# 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)
+```
+
+**CosyVoice Usage**
+```python
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=False, load_trt=False, fp16=False)
+# sft usage
+print(cosyvoice.list_available_spks())
+# change stream=True for chunk stream inference
+for i, j in enumerate(cosyvoice.inference_sft('你好，我是通义生成式语音大模型，请问有什么可以帮您的吗？', '中文女', stream=False)):
+    torchaudio.save('sft_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M') # or change to pretrained_models/CosyVoice-300M-25Hz for 25Hz inference
+# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
+prompt_speech_16k = load_wav('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)
+# cross_lingual usage
+prompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
+for i, j in enumerate(cosyvoice.inference_cross_lingual('<|en|>And then later on, fully acquiring that company. So keeping management in line, interest in line with the asset that\'s coming into the family is a reason why sometimes we don\'t buy the whole thing.', prompt_speech_16k, stream=False)):
+    torchaudio.save('cross_lingual_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+# vc usage
+prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
+source_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
+for i, j in enumerate(cosyvoice.inference_vc(source_speech_16k, prompt_speech_16k, stream=False)):
+    torchaudio.save('vc_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+
+cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-Instruct')
+# instruct usage, support <laughter></laughter><strong></strong>[laughter][breath]
+for i, j in enumerate(cosyvoice.inference_instruct('在面对挑战时，他展现了非凡的<strong>勇气</strong>与<strong>智慧</strong>。', '中文男', 'Theo \'Crimson\', is a fiery, passionate rebel leader. Fights with fervor for justice, but struggles with impulsiveness.', stream=False)):
+    torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+```
+
+**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 user, we have provided train and inference scripts in `examples/libritts/cosyvoice/run.sh`.
+
+**Build for deployment**
+
+Optionally, if you want service deployment,
+you can run 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>
+```
+
+## 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).
+
+## 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.

CosyVoice2-0.5B/campplus.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ac6a63997761ae2997373e2ee1c47040854b4b759ea41ec48e4e42df0f4d73
+size 28303423

CosyVoice2-0.5B/configuration.json

@@ -0,0 +1,4 @@
+{
+    "framework": "Pytorch",
+    "task": "text-to-speech"
+}

CosyVoice2-0.5B/cosyvoice2.yaml

@@ -0,0 +1,233 @@
+# 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.Qwen2LM
+    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.CausalMaskedDiffWithXvec
+    input_size: 512
+    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
+    encoder:
+        !new:cosyvoice.transformer.upsample_encoder.UpsampleConformerEncoder
+        output_size: 512
+        attention_heads: 8
+        linear_units: 2048
+        num_blocks: 6
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.1
+        normalize_before: True
+        input_layer: "linear"
+        pos_enc_layer_type: "rel_pos_espnet"
+        selfattention_layer_type: "rel_selfattn"
+        input_size: 512
+        use_cnn_module: False
+        macaron_style: False
+        static_chunk_size: !ref <chunk_size>
+    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.decoder.CausalConditionalDecoder
+            in_channels: 320
+            out_channels: 80
+            channels: [256]
+            dropout: 0.0
+            attention_head_dim: 64
+            n_blocks: 4
+            num_mid_blocks: 12
+            num_heads: 8
+            act_fn: "gelu"
+            static_chunk_size: !ref <chunk_size> * <token_mel_ratio>
+            num_decoding_left_chunks: !ref <num_decoding_left_chunks>
+
+hift: !new:cosyvoice.hifigan.generator.HiFTGenerator
+    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
+    f0_predictor: !new:cosyvoice.hifigan.f0_predictor.ConvRNNF0Predictor
+        num_class: 1
+        in_channels: 80
+        cond_channels: 512
+
+# gan related module
+mel_spec_transform1: !name:cosyvoice.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
+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:cosyvoice.utils.audio.mel_spectrogram
+    n_fft: 1920
+    num_mels: 80
+    sampling_rate: !ref <sample_rate>
+    hop_size: 480
+    win_size: 1920
+    fmin: 0
+    fmax: 8000
+    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

CosyVoice2-0.5B/flow.decoder.estimator.fp32.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd54e4281701e6630730da64502d77b7e8b6e5c057cca65128bffb50f85cbf98
+size 286317026

CosyVoice2-0.5B/flow.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4c2f867674411e0a08cee702996df13fa67c1cd864c06108da88d16d088541
+size 450575567

CosyVoice2-0.5B/hift.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3386cc880324d4e98e05987b99107f49e40ed925b8ecc87c1f4939432d429879
+size 83390254

CosyVoice2-0.5B/llm.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b144ef55b51ce8cfb79a73c90dbba0bdaba4e451c0ebcfab20f769264f84a608
+size 2023316821

CosyVoice2-0.5B/speech_tokenizer_v2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43342aa12163a80bf07bffb94c9de2e120a8df2f9917cd2f642e7f4219c6f71
+size 496082973

spk2info.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652d571b2efec1be6dc14345c2bae52eb41affe4b5d3fa4174548e059bd633b4
+size 1317821