mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-24 06:48:58 +06:00
0234de8418
* add encode labels function to tokenizer * start adding finetuning * init dropout * upload * correct convert script * apply changes * fix second typo * make first dummy training run * adapt convert script * push confg for comparison * remove conf * finish training * adapt data collator * add research folder * update according to fairseq feedback * some minor corrections * refactor masking indices a bit * some minor changes * clean tokenizer * finish clean-up * remove previous logic * update run script * correct training * finish changes * finish model * correct bug * fix training a bit more * add some tests * finish gradient checkpointing * finish example * correct gradient checkpointing * improve tokenization method * revert changes in tokenizer * revert general change * adapt fine-tuning * update * save intermediate test * Update README.md * finish finetuning * delete conversion script * Update src/transformers/models/wav2vec2/configuration_wav2vec2.py * Update src/transformers/models/wav2vec2/processing_wav2vec2.py Co-authored-by: Lysandre Debut <lysandre@huggingface.co> * finish wav2vec2 script * finish wav2vec2 fine-tuning * finalize test * correct test * adapt tests * finish * remove test file Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
9 lines
568 B
Markdown
9 lines
568 B
Markdown
## Fine-tuning Wav2Vec2
|
|
|
|
The `run_training.py` script allows one to finetune pretrained Wav2Vec2 models that can be found [here](https://huggingface.co/models?search=facebook/wav2vec2).
|
|
|
|
This finetuning script can also be run as a google colab [TODO: here]( ).
|
|
|
|
The script is actively maintained by [Patrick von Platen](https://github.com/patrickvonplaten).
|
|
Feel free to ask a question on the [Forum](https://discuss.huggingface.co/) or post an issue on [GitHub](https://github.com/huggingface/transformers/issues/new/choose) and adding `@patrickvonplaten` as a tag.
|