Automatic Speech Recognition
Transformers
PyTorch
Hindi
wav2vec2
audio
speech
Eval Results (legacy)
Eval Results
Instructions to use Harveenchadha/vakyansh-wav2vec2-hindi-him-4200 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Harveenchadha/vakyansh-wav2vec2-hindi-him-4200 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Harveenchadha/vakyansh-wav2vec2-hindi-him-4200")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Harveenchadha/vakyansh-wav2vec2-hindi-him-4200") model = AutoModelForCTC.from_pretrained("Harveenchadha/vakyansh-wav2vec2-hindi-him-4200") - Notebooks
- Google Colab
- Kaggle
Error while running inference of hindi speech recognition model
#2
by Sandhya1210 - opened
Expected 2D (unbatched) or 3D (batched) input to conv1d, but got input of size: [1, 1, 36223, 2]
i am getting this error while trying to run the inference code
Facing Same error. Did you get any lead?
facing same error, any leads?