Model reference · open weights
wav2vec2-large-xlsr-53-th-c-newmm is an open-weight audio or speech model from wannaphong. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | wannaphong |
|---|---|
| Type | Audio & music |
| Task | Speech→text |
| Parameters (lead) | 316M |
| Runs with | transformers |
| Released | 2022-06-06 |
| Popularity | 2k downloads / month |
| Licence | Open weights |
About
This model trained with CommonVoice V8 dataset by increase data from CommonVoice V7 dataset that It was use in airesearch/wav2vec2-large-xlsr-53-th. It was finetune wav2vec2-large-xlsr-53.
It is increase new data from The Common Voice V8 dataset to Common Voice V7 dataset or remove all data in Common Voice V7 dataset before split Common Voice V8 then add CommonVoice V7 dataset back to dataset.
It use ekapolc/Thai_commonvoice_split script for split Common Voice dataset.
This model was finetune wav2vec2-large-xlsr-53 model with Thai Common Voice V8 dataset and It use pre-tokenize with pythainlp.tokenize.word_tokenize.
I used many code from vistec-AI/wav2vec2-large-xlsr-53-th and I fixed bug training code in vistec-AI/wav2vec2-large-xlsr-53-th#2
Test with CommonVoice V8 Testset
| Model | WER by newmm (%) | WER by deepcut (%) | CER |
|---|---|---|---|
| AIResearch.in.th and PyThaiNLP | 17.414503 | 11.923089 | 3.854153 |
| wav2vec2 with deepcut | 16.354521 | 11.424476 | 3.684060 |
| wav2vec2 with newmm | 16.698299 | 11.436941 | 3.737407 |
| wav2vec2 with deepcut + language model | 12.630260 | 9.613886 | 3.292073 |
| wav2vec2 with newmm + language model | 12.583706 | 9.598305 | 3.276610 |
Test with CommonVoice V7 Testset (same test by CV V7)
| Model | WER by newmm (%) | WER by deepcut (%) | CER |
|---|---|---|---|
| AIResearch.in.th and PyThaiNLP | 13.936698 | 9.347462 | 2.804787 |
| wav2vec2 with deepcut | 12.776381 | 8.773006 | 2.628882 |
| wav2vec2 with newmm | 12.750596 | 8.672616 | 2.623341 |
| wav2vec2 with deepcut + language model | 9.940050 | 7.423313 | 2.344940 |
| wav2vec2 with newmm + language model | 9.559724 | 7.339654 | 2.277071 |
This is use same testset from https://huggingface.co/airesearch/wav2vec2-large-xlsr-53-th.
Links:
@misc{phatthiyaphaibun2022thai,
title={Thai Wav2Vec2.0 with CommonVoice V8},
author={Wannaphong Phatthiyaphaibun and Chompakorn Chaksangchaichot and Peerat Limkonchotiwat and Ekapol Chuangsuwanich and Sarana Nutanong},
year={2022},
eprint={2208.04799},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys wav2vec2-large-xlsr-53-th-c-newmm for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-xlsr-53-th-c-newmm below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="wav2vec2-large-xlsr-53-th-c-newmm" -F file=@audio.mp3
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.