Automatic Speech Recognition
Transformers
PyTorch
Hindi
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use nikhilbh/whisper-large-v2-custom-hi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nikhilbh/whisper-large-v2-custom-hi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nikhilbh/whisper-large-v2-custom-hi")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("nikhilbh/whisper-large-v2-custom-hi") model = AutoModelForMultimodalLM.from_pretrained("nikhilbh/whisper-large-v2-custom-hi") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 24.45, | |
| "eval_loss": 0.33888712525367737, | |
| "eval_runtime": 1885.1253, | |
| "eval_samples": 2894, | |
| "eval_samples_per_second": 1.535, | |
| "eval_steps_per_second": 0.192, | |
| "eval_wer": 0.21857275882502328 | |
| } |