Automatic Speech Recognition
Transformers
PyTorch
Thai
wav2vec2
audio
hf-asr-leaderboard
robust-speech-event
speech
xlsr-fine-tuning
Eval Results (legacy)
Instructions to use airesearch/wav2vec2-large-xlsr-53-th with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use airesearch/wav2vec2-large-xlsr-53-th with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="airesearch/wav2vec2-large-xlsr-53-th")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("airesearch/wav2vec2-large-xlsr-53-th") model = AutoModelForCTC.from_pretrained("airesearch/wav2vec2-large-xlsr-53-th") - Notebooks
- Google Colab
- Kaggle