Automatic Speech Recognition
NeMo
Japanese
speech
audio
japanese
TDT
FastConformer
Conformer
KDA
NeMo
Instructions to use third-intelligence/Haas-ja-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use third-intelligence/Haas-ja-v1.0 with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("third-intelligence/Haas-ja-v1.0") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Commit History
Today
-
Model card: link to the demo app
Verified signature660728d -
Model card: add the blog link
Verified signature29e3087
Yesterday
-
Model card: results with the newly added models
Verified signature8a36fd5
4 days ago
-
Model card: custom vocabulary, speaker labels and updated limitations
Verified signatureAdds the custom vocabulary and the speaker-label example (with NVIDIA's Nemotron-3-Diarization) to How to use, names GPT-Transcribe as on par in the results, updates the limitations to match, adds a link to the demo Space, and follows the inference code's changes (Python 3.11+, example file names).efd7b81
8 days ago
-
Haas-ja-v1.0: weights, config, model card and figures
8474e1e