Automatic Speech Recognition
Transformers
Safetensors
PyTorch
Malagasy
whisper
deprecated
speech
speech-recognition
malagasy
low-resource
african-languages
madagascar
fine-tuned
Eval Results (legacy)
Instructions to use Flo976/whisper-malagasy-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Flo976/whisper-malagasy-medium with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Flo976/whisper-malagasy-medium")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Flo976/whisper-malagasy-medium") model = AutoModelForSpeechSeq2Seq.from_pretrained("Flo976/whisper-malagasy-medium", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from Flo976/whisper-malagasy-medium: direct link, hf CLI and curl.
- Browser
- Download file 6.11 GB
-
https://huggingface.co/Flo976/whisper-malagasy-medium/resolve/main/optimizer.pt
- Command line
-
hf download hf://Flo976/whisper-malagasy-medium/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/Flo976/whisper-malagasy-medium/resolve/main/optimizer.pt
6.11 GB
- Xet hash:
- 914073f8c75b8e4a666c2dce0840827bc3081124d7bc02a4137a6d43d236135c
- Size of remote file:
- 6.11 GB
- SHA256:
- 9d7e195385c0a2abcfa85b2acbd5be48bfc2bd018cc1ec0893c3c1e888af63ce
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.