Automatic Speech Recognition
Transformers
PyTorch
Ganda
wav2vec2
audio
common_voice
hf-asr-leaderboard
robust-speech-event
speech
Eval Results (legacy)
Instructions to use cahya/wav2vec2-luganda with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cahya/wav2vec2-luganda with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="cahya/wav2vec2-luganda")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("cahya/wav2vec2-luganda") model = AutoModelForCTC.from_pretrained("cahya/wav2vec2-luganda", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- f52585b7f70146e1c7f767add68be5e62805dd05ab2612c7c5e6d33bb36921dd
- Size of remote file:
- 1.26 GB
- SHA256:
- 447bf4c640af086f70af1eaeca3850c694f9d56aa085922fd02839673b611805
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.