Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ssbuild/asr_ctc_finetuning
https://github.com/ssbuild/asr_ctc_finetuning
Last synced: 4 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/ssbuild/asr_ctc_finetuning
- Owner: ssbuild
- License: apache-2.0
- Created: 2023-10-23T09:08:31.000Z (about 1 year ago)
- Default Branch: dev
- Last Pushed: 2023-11-03T07:10:27.000Z (about 1 year ago)
- Last Synced: 2024-04-28T04:59:04.953Z (7 months ago)
- Language: Python
- Size: 8.88 MB
- 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 ctc
```
## 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
- [wav2vec2-base-100h](https://huggingface.co/facebook/wav2vec2-base-100h)
- [wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h)
- [wav2vec2-large-960h](https://huggingface.co/facebook/wav2vec2-large-960h)
- [wav2vec2-large-960h-lv60-self](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self)
- [wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base)
- [wav2vec2-large](https://huggingface.co/facebook/wav2vec2-large)
- [wavlm-base-plus](https://huggingface.co/microsoft/wavlm-base-plus)
- [wavlm-base](https://huggingface.co/microsoft/wavlm-base)
## data sample
- open_data https://github.com/ssbuild/open_data
- librispeech_asr_dummy https://huggingface.co/datasets/patrickvonplaten/librispeech_asr_dummy
单条数据示例
```json
{"file": "../assets/librispeech_asr_dummy/1272-128104-0000.flac", "sentence": "MISTER QUILTER IS THE APOSTLE OF THE MIDDLE CLASSES AND WE ARE GLAD TO WELCOME HIS GOSPEL"}
```
## 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
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
```
## 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
## 参考
https://github.com/facebookresearch/fairseq/tree/main/examples/wav2vec#wav2vec-20
## Star History
[](https://star-history.com/#ssbuild/asr_ctc_finetuning&Date)