Views
No views yet
1from speechbrain.inference import EncoderASR
2
3asr_model = EncoderASR.from_hparams(
4 source="fortunedavis/afrihubert_fongbe_asr",
5 savedir="pretrained_models/afrihubert_fongbe_asr",
6 run_opts=run_opts
7)
8
9asr_model.transcribe_file("your_file.wav")| Dataset | WER |
|---|---|
| FFSTC-2 | 21% |
1@inproceedings{kponou25_interspeech,
2 title = {{Extending the Fongbe to French Speech Translation Corpus: resources, models and benchmark}},
3 author = {D. Fortuné Kponou and Salima Mdhaffar and Fréjus A. A. Laleye and Eugène C. Ezin and Yannick Estève},
4 year = {2025},
5 booktitle = {{Interspeech 2025}},
6 pages = {4533--4537},
7 doi = {10.21437/Interspeech.2025-1801},
8 issn = {2958-1796},
9}