Instructions to use mlengineer-ai/whisper-small-fa-specaug with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlengineer-ai/whisper-small-fa-specaug with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mlengineer-ai/whisper-small-fa-specaug")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("mlengineer-ai/whisper-small-fa-specaug") model = AutoModelForSpeechSeq2Seq.from_pretrained("mlengineer-ai/whisper-small-fa-specaug", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-24000/pytorch_model.bin from mlengineer-ai/whisper-small-fa-specaug: direct link, hf CLI and curl.
- Browser
- Download file 967 MB
-
https://huggingface.co/mlengineer-ai/whisper-small-fa-specaug/resolve/main/checkpoint-24000/pytorch_model.bin
- Command line
-
hf download hf://mlengineer-ai/whisper-small-fa-specaug/checkpoint-24000/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/mlengineer-ai/whisper-small-fa-specaug/resolve/main/checkpoint-24000/pytorch_model.bin
967 MB
- Xet hash:
- 632e0420efb8fc0f1eeca07c67a38202bf159892344380d3c2aab5c864f46b20
- Size of remote file:
- 967 MB
- SHA256:
- 45cbcae625dcfa89300c5141f57ee34c595b2f1747de117a51a1e8981217a94a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.