Ver código fonte

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

update
Xiang Lyu 11 meses atrás
pai
commit
81edc83648
3 arquivos alterados com 4 adições e 3 exclusões
  1. 2 2
      README.md
  2. 1 0
      cosyvoice/bin/export_trt.sh
  3. 1 1
      cosyvoice/cli/cosyvoice.py

+ 2 - 2
README.md

@@ -63,7 +63,7 @@ git submodule update --init --recursive
 - Create Conda env:
 
 ``` sh
-conda create -n cosyvoice python=3.8
+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
@@ -78,7 +78,7 @@ 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.
+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.
 

+ 1 - 0
cosyvoice/bin/export_trt.sh

@@ -1,4 +1,5 @@
 #!/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
 # 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>

+ 1 - 1
cosyvoice/cli/cosyvoice.py

@@ -142,7 +142,7 @@ class CosyVoice2(CosyVoice):
         if not os.path.exists(model_dir):
             model_dir = snapshot_download(model_dir)
         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'],
                                           configs['feat_extractor'],
                                           '{}/campplus.onnx'.format(model_dir),