Automatic Speech Recognition
Transformers
Safetensors
Akan
Twi
whisper
ASR
Akan
low-resource-language
speech-recognition
Instructions to use GiftMark/akan-whisper-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GiftMark/akan-whisper-model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="GiftMark/akan-whisper-model")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("GiftMark/akan-whisper-model") model = AutoModelForSpeechSeq2Seq.from_pretrained("GiftMark/akan-whisper-model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Licence for akan-whisper-model?
#2
by tsotsoobi - opened
Hi Mark, thank you for publishing this model.
I'm building a local-first Twi transcription app for Ghanaian users. Speech is processed on the user's own computer, and I would like to use akan-whisper-model in it.
The model card doesn't state a licence. Could you add one, or tell me here which terms apply? The base model, openai/whisper-small, is MIT licensed. I'd also like to know whether commercial use is allowed.
Happy to credit you in the app.
Adokwei Addo, Pi Logistics Ltd, Accra