Automatic Speech Recognition
Transformers
PyTorch
Hindi
wav2vec2
Openslr Multilingual
Generated from Trainer
hf-asr-leaderboard
mozilla-foundation/common_voice_7_0
robust-speech-event
Eval Results (legacy)
Instructions to use LegolasTheElf/Wav2Vec2_xls_r_lm_300m_hi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LegolasTheElf/Wav2Vec2_xls_r_lm_300m_hi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="LegolasTheElf/Wav2Vec2_xls_r_lm_300m_hi")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("LegolasTheElf/Wav2Vec2_xls_r_lm_300m_hi") model = AutoModelForCTC.from_pretrained("LegolasTheElf/Wav2Vec2_xls_r_lm_300m_hi") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 4cf49d598b1b709c0a8eb031011e16bb4c0cf6598c861d34833b6333d2f05b88
- Size of remote file:
- 1.26 GB
- SHA256:
- 85abd203b9d5666bd41435170093cb2eac516e0dae37fa291826a38f2c8fd491
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.