Instructions to use EricChang/Taiwanese-Whisper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EricChang/Taiwanese-Whisper with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="EricChang/Taiwanese-Whisper")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("EricChang/Taiwanese-Whisper") model = AutoModelForSpeechSeq2Seq.from_pretrained("EricChang/Taiwanese-Whisper", device_map="auto") - Notebooks
- Google Colab
- Kaggle
support for AutoProcessor and generation config
#2
by Splend1dchan - opened
Hi Eric,
Great work!
Would you mind adding merges.txt and generation_config.json?
This would be very helpful for the automated loading of your model, which is essential in one of my projects: https://github.com/mtkresearch/generative-fusion-decoding
Here is the link to show what I mean: https://huggingface.co/Splend1dchan/Taiwanese-Whisper