Instructions to use nectec/Pathumma-whisper-th-large-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nectec/Pathumma-whisper-th-large-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nectec/Pathumma-whisper-th-large-v3")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("nectec/Pathumma-whisper-th-large-v3") model = AutoModelForSpeechSeq2Seq.from_pretrained("nectec/Pathumma-whisper-th-large-v3") - Notebooks
- Google Colab
- Kaggle
FYI: MLX-format conversion for Apple Silicon
#1
by kinoppy555 - opened
Hi NECTEC team β thank you for releasing Pathumma!
I've published an MLX-format conversion for Apple Silicon Mac users:
https://huggingface.co/kinoppy555/Pathumma-whisper-th-large-v3-mlx
It's a format-only conversion (FP16, no retraining), Apache 2.0 inherited, clearly labeled as unofficial. Happy to adjust the README or transfer to mlx-community if you'd prefer.
Thanks!