Instructions to use jonatasgrosman/exp_w2v2t_en_unispeech-sat_s456 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jonatasgrosman/exp_w2v2t_en_unispeech-sat_s456 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="jonatasgrosman/exp_w2v2t_en_unispeech-sat_s456")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("jonatasgrosman/exp_w2v2t_en_unispeech-sat_s456") model = AutoModelForCTC.from_pretrained("jonatasgrosman/exp_w2v2t_en_unispeech-sat_s456", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download transcriptions_cv7_validation.json from jonatasgrosman/exp_w2v2t_en_unispeech-sat_s456: direct link, hf CLI and curl.
- Browser
- Download file 80.9 MB
-
https://huggingface.co/jonatasgrosman/exp_w2v2t_en_unispeech-sat_s456/resolve/main/transcriptions_cv7_validation.json
- Command line
-
hf download hf://jonatasgrosman/exp_w2v2t_en_unispeech-sat_s456/transcriptions_cv7_validation.json
-
curl -L -o transcriptions_cv7_validation.json https://huggingface.co/jonatasgrosman/exp_w2v2t_en_unispeech-sat_s456/resolve/main/transcriptions_cv7_validation.json
80.9 MB
- Xet hash:
- 76455b7b85e2eeef43a0ad1e83a38c86bd43faf8388d8d5c31a6637afc647f28
- Size of remote file:
- 80.9 MB
- SHA256:
- 379879a56d27d80b11139f2dbc202df6c0b0df4dcb4dc7e06904e738dca34787
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.