Instructions to use Priyanship/eval_cache_hindi_only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Priyanship/eval_cache_hindi_only with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Priyanship/eval_cache_hindi_only")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Priyanship/eval_cache_hindi_only") model = AutoModelForCTC.from_pretrained("Priyanship/eval_cache_hindi_only", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "eval_cer": 0.4629913780505626, | |
| "eval_loss": 2.218759059906006, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 40.9239, | |
| "eval_samples": 572, | |
| "eval_samples_per_second": 13.977, | |
| "eval_steps_per_second": 0.88, | |
| "eval_wer": 0.5242065233289455 | |
| } |