Automatic Speech Recognition
Transformers
Safetensors
Mobilint
mobilint-whisper
text-generation
custom_code
Instructions to use mobilint/whisper-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mobilint/whisper-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mobilint/whisper-small", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("mobilint/whisper-small", trust_remote_code=True, device_map="auto") - Mobilint
How to use mobilint/whisper-small with Mobilint:
# pip install mblt-model-zoo from mblt_model_zoo.vision import MBLT_Engine model = MBLT_Engine( model_cls="whisper-small", model_type="DEFAULT", model_path="", core_mode="global8", ) try: image = model.preprocess("path/to/image.jpg") output = model(image) result = model.postprocess(output) finally: model.dispose() - Notebooks
- Google Colab
- Kaggle
Download whisper-small_decoder.mxq from mobilint/whisper-small: direct link, hf CLI and curl.
- Browser
- Download file 167 MB
-
https://huggingface.co/mobilint/whisper-small/resolve/main/whisper-small_decoder.mxq
- Command line
-
hf download hf://mobilint/whisper-small/whisper-small_decoder.mxq
-
curl -L -o whisper-small_decoder.mxq https://huggingface.co/mobilint/whisper-small/resolve/main/whisper-small_decoder.mxq
167 MB
- Xet hash:
- 19978b66bc1b58c3872b8c9c735141262bdafc2c994ce0239168fa373bf08696
- Size of remote file:
- 167 MB
- SHA256:
- f2d187c325b73ceeae396f86905b79ff48a41043b28ff4be5517a64fd6f57d98
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.