deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-05 18:09:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #728 from FunAudioLLM/dev/lyuxiang.lx

Browse Source 
update
This commit is contained in:
Xiang Lyu
2024-12-16 15:34:26 +08:00
committed by GitHub
parent 32e6684025 60b0416229
commit 81edc83648
3 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -63,7 +63,7 @@ git submodule update --init --recursive
- Create Conda env: - Create Conda env:
``` sh ``` sh
conda create -n cosyvoice python=3.8 conda create -n cosyvoice python=3.10
conda activate cosyvoice conda activate cosyvoice
# pynini is required by WeTextProcessing, use conda to install it as it can be executed on all platform. # 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 conda install -y -c conda-forge pynini==2.1.5
@@ -78,7 +78,7 @@ sudo yum install sox sox-devel
**Model download** **Model download**
We strongly recommend that you download our pretrained `CosyVoice-300M` `CosyVoice-300M-SFT` `CosyVoice-300M-Instruct` model and `CosyVoice-ttsfrd` resource. We strongly recommend that you download our pretrained `CosyVoice2-0.5B` `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. 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.

1
cosyvoice/bin/export_trt.sh
View File

@@ -1,4 +1,5 @@
#!/bin/bash #!/bin/bash
# Copyright 2024 Alibaba Inc. All Rights Reserved.
# download tensorrt from https://developer.nvidia.com/tensorrt/download/10x, check your system and cuda for compatibability # download tensorrt from https://developer.nvidia.com/tensorrt/download/10x, check your system and cuda for compatibability
# for example for linux + cuda12.4, you can download https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.0.1/tars/TensorRT-10.0.1.6.Linux.x86_64-gnu.cuda-12.4.tar.gz # for example for linux + cuda12.4, you can download https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.0.1/tars/TensorRT-10.0.1.6.Linux.x86_64-gnu.cuda-12.4.tar.gz
TRT_DIR=<YOUR_TRT_DIR> TRT_DIR=<YOUR_TRT_DIR>

2
cosyvoice/cli/cosyvoice.py
View File

@@ -142,7 +142,7 @@ class CosyVoice2(CosyVoice):
if not os.path.exists(model_dir): if not os.path.exists(model_dir):
model_dir = snapshot_download(model_dir) model_dir = snapshot_download(model_dir)
with open('{}/cosyvoice.yaml'.format(model_dir), 'r') as f: with open('{}/cosyvoice.yaml'.format(model_dir), 'r') as f:
configs = load_hyperpyyaml(f, overrides={'qwen_pretrain_path': os.path.join(model_dir, 'Qwen2-0.5B-CosyVoice-BlankEN')}) configs = load_hyperpyyaml(f, overrides={'qwen_pretrain_path': os.path.join(model_dir, 'CosyVoice-BlankEN')})
self.frontend = CosyVoiceFrontEnd(configs['get_tokenizer'], self.frontend = CosyVoiceFrontEnd(configs['get_tokenizer'],
configs['feat_extractor'], configs['feat_extractor'],
'{}/campplus.onnx'.format(model_dir), '{}/campplus.onnx'.format(model_dir),