Automatic Speech Recognition
Transformers
PyTorch
Malayalam
English
wav2vec2
malayalam
ml_en
code-switching
Eval Results (legacy)
Instructions to use erose/wav2vec2-malayalam_english-3h with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use erose/wav2vec2-malayalam_english-3h with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="erose/wav2vec2-malayalam_english-3h")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("erose/wav2vec2-malayalam_english-3h") model = AutoModelForCTC.from_pretrained("erose/wav2vec2-malayalam_english-3h") - Notebooks
- Google Colab
- Kaggle
README.md exists but content is empty.
- Downloads last month
- 7
Evaluation results
- Test WER on erose/code_switching-ml-en (test set)self-reported58.930
- Test CER on erose/code_switching-ml-en (test set)self-reported19.450