https://github.com/ssbuild/asr_seq2seq_finetuning
https://github.com/ssbuild/asr_seq2seq_finetuning
Last synced: 11 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/ssbuild/asr_seq2seq_finetuning
- Owner: ssbuild
- License: apache-2.0
- Created: 2023-10-21T06:35:50.000Z (over 2 years ago)
- Default Branch: dev
- Last Pushed: 2023-11-03T07:15:23.000Z (over 2 years ago)
- Last Synced: 2025-02-22T01:19:59.987Z (over 1 year ago)
- Language: Python
- Size: 461 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.MD
- License: LICENSE
Awesome Lists containing this project
README
## update information
- [deep_training](https://github.com/ssbuild/deep_training)
```text
10-24 initial asr seq2seq
```
## install
- pip install -U -r requirements.txt
- 如果无法安装， 可以切换官方源 pip install -i https://pypi.org/simple -U -r requirements.txt
## weigtht select one is suitable for you
支持且不限于以下权重
- [whisper-large-v2](https://huggingface.co/openai/whisper-large-v2)
- [whisper-large](https://huggingface.co/openai/whisper-large)
- [whisper-base](https://huggingface.co/openai/whisper-base)
- [whisper-small](https://huggingface.co/openai/whisper-small)
- [whisper-tiny](https://huggingface.co/openai/whisper-tiny)
- [speecht5_asr](https://huggingface.co/microsoft/speecht5_asr)
## data sample
- open_data https://github.com/ssbuild/open_data
- common_voice_11_0 https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0
- common_voice https://huggingface.co/datasets/common_voice
单条数据示例
```json
{
"path": "../zh-CN_train_0/common_voice_zh-CN_33211332.mp3",
"sentence": "性喜温暖润湿气候且耐寒。",
"locale": "zh-CN"
}
```
## infer
# infer_finetuning.py 推理微调模型
# infer_lora_finetuning.py 推理微调模型
python infer_finetuning.py
## training
```text
# 制作数据
cd scripts
bash train_full.sh -m dataset
or
bash train_lora.sh -m dataset
or
bash train_ptv2.sh -m dataset
注: num_process_worker 为多进程制作数据 ， 如果数据量较大 ， 适当调大至cpu数量
dataHelper.make_dataset_with_args(data_args.train_file,mixed_data=False, shuffle=True,mode='train',num_process_worker=0)
# 全参数训练
bash train_full.sh -m train
# lora adalora ia3
bash train_lora.sh -m train
# ptv2
bash train_ptv2.sh -m train
```
## 训练参数
[训练参数](args.MD)
## 友情链接
- [pytorch-task-example](https://github.com/ssbuild/pytorch-task-example)
- [tf-task-example](https://github.com/ssbuild/tf-task-example)
- [chatmoss_finetuning](https://github.com/ssbuild/chatmoss_finetuning)
- [chatglm_finetuning](https://github.com/ssbuild/chatglm_finetuning)
- [t5_finetuning](https://github.com/ssbuild/t5_finetuning)
- [llm_finetuning](https://github.com/ssbuild/llm_finetuning)
- [llm_rlhf](https://github.com/ssbuild/llm_rlhf)
- [chatglm_rlhf](https://github.com/ssbuild/chatglm_rlhf)
- [t5_rlhf](https://github.com/ssbuild/t5_rlhf)
- [rwkv_finetuning](https://github.com/ssbuild/rwkv_finetuning)
- [baichuan_finetuning](https://github.com/ssbuild/baichuan_finetuning)
##
纯粹而干净的代码
## Star History
[](https://star-history.com/#ssbuild/asr_seq2seq_finetuning&Date)