Instructions to use vasudevgupta/speech_jax_wav2vec2-large-lv60_960h with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vasudevgupta/speech_jax_wav2vec2-large-lv60_960h with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="vasudevgupta/speech_jax_wav2vec2-large-lv60_960h")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("vasudevgupta/speech_jax_wav2vec2-large-lv60_960h") model = AutoModelForCTC.from_pretrained("vasudevgupta/speech_jax_wav2vec2-large-lv60_960h", device_map="auto") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
- Evaluation Notebook: https://colab.research.google.com/drive/1dV1Z3WajMCYMjNZab98CEEcg3FTbtONO?usp=sharing
- Training Code: https://github.com/vasudevgupta7/speech-jax/blob/main/projects/finetune_wav2vec2.py
- Weights & Biases: https://wandb.ai/7vasudevgupta/speech-JAX?workspace=user-7vasudevgupta
Following results are obtained with 23ffe236840b7f75c9f01a9c347b01485a2bf9f6 & 95c3bc1b83c74452df29f792e0b5651c09fdaeb9
| dataset | WER |
|---|---|
| Librispeech-test-clean | 3.3 % |
- Downloads last month
- 8