Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
audio
speech
african-languages
multilingual
simba
low-resource
speech-recognition
asr
Instructions to use UBC-NLP/Simba-X with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UBC-NLP/Simba-X with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="UBC-NLP/Simba-X")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("UBC-NLP/Simba-X") model = AutoModelForCTC.from_pretrained("UBC-NLP/Simba-X", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from UBC-NLP/Simba-X: direct link, hf CLI and curl.
- Browser
- Download file 3.85 GB
-
https://huggingface.co/UBC-NLP/Simba-X/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://UBC-NLP/Simba-X/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/UBC-NLP/Simba-X/resolve/main/pytorch_model.bin
3.85 GB
- Xet hash:
- 469142fdc9acf9aecf62f13c725db1949a4c9af58a75c7625ca649b8bb5dded1
- Size of remote file:
- 3.85 GB
- SHA256:
- 55dadad20e78450a398a164fc4f9ec8f18459ea683ca466c894ebcc3fdbc2320
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.