Model reference · open weights
DPRNNTasNet-ks16_WHAM_sepclean is an open-weight audio or speech model from julien-c. 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
| Maker | julien-c |
|---|---|
| Type | Audio & music |
| Task | Audio→audio |
| Runs with | asteroid |
| Released | 2022-03-02 |
| Popularity | 2k downloads / month |
| Licence | Open weights |
About
mpariente/DPRNNTasNet(ks=16)_WHAM!_sepclean♻️ Imported from https://zenodo.org/record/3903795#.X8pMBRNKjUI
This model was trained by Manuel Pariente using the wham/DPRNN recipe in Asteroid. It was trained on the sep_clean task of the WHAM! dataset.
# coming soon
si_sdr: 18.227683982688003si_sdr_imp: 18.22883576588251sdr: 18.617789605060587sdr_imp: 18.466745426438173sir: 29.22773720052717sir_imp: 29.07669302190474sar: 19.116352171914485sar_imp: -130.06009796503054stoi: 0.9722025377865715stoi_imp: 0.23415680987800583@inproceedings{Pariente2020Asteroid,
title={Asteroid: the {PyTorch}-based audio source separation toolkit for researchers},
author={Manuel Pariente and Samuele Cornell and Joris Cosentino and Sunit Sivasankaran and
Efthymios Tzinis and Jens Heitkaemper and Michel Olvera and Fabian-Robert Stöter and
Mathieu Hu and Juan M. Martín-Doñas and David Ditter and Ariel Frank and Antoine Deleforge
and Emmanuel Vincent},
year={2020},
booktitle={Proc. Interspeech},
}
Or on arXiv:
@misc{pariente2020asteroid,
title={Asteroid: the PyTorch-based audio source separation toolkit for researchers},
author={Manuel Pariente and Samuele Cornell and Joris Cosentino and Sunit Sivasankaran and Efthymios Tzinis and Jens Heitkaemper and Michel Olvera and Fabian-Robert Stöter and Mathieu Hu and Juan M. Martín-Doñas and David Ditter and Ariel Frank and Antoine Deleforge and Emmanuel Vincent},
year={2020},
eprint={2005.04132},
archivePrefix={arXiv},
primaryClass={eess.AS}
}
From the published model card. Full card on the HuggingFace links in the sidebar.
How it works
Using it via the API
Once AxForge deploys dprnntasnet-ks16-wham-sepclean for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (dprnntasnet-ks16-wham-sepclean 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="dprnntasnet-ks16-wham-sepclean" -F file=@audio.mp3
Create an account — your API key is available in the console. 5M tokens/month currently included with every new account at launch.