Automatic Speech Recognition
Transformers
Safetensors
Hindi
wav2vec2
mozilla-foundation/common_voice_15_0
mms
Generated from Trainer
Eval Results (legacy)
Instructions to use RSK1987/Output with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RSK1987/Output with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="RSK1987/Output")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("RSK1987/Output") model = AutoModelForCTC.from_pretrained("RSK1987/Output", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download all_results.json from RSK1987/Output: direct link, hf CLI and curl.
- Browser
- Download file 451 Bytes
-
https://huggingface.co/RSK1987/Output/resolve/main/all_results.json
- Command line
-
hf download hf://RSK1987/Output/all_results.json
-
curl -L -o all_results.json https://huggingface.co/RSK1987/Output/resolve/main/all_results.json
451 Bytes
| { | |
| "epoch": 1.0, | |
| "eval_loss": 20.228919982910156, | |
| "eval_runtime": 119.2704, | |
| "eval_samples": 2416, | |
| "eval_samples_per_second": 20.256, | |
| "eval_steps_per_second": 2.532, | |
| "eval_wer": 1.0016248153618907, | |
| "total_flos": 6.105598680744346e+17, | |
| "train_loss": 18.507504377693966, | |
| "train_runtime": 329.6848, | |
| "train_samples": 4630, | |
| "train_samples_per_second": 14.044, | |
| "train_steps_per_second": 0.44 | |
| } |