Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Oriya
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use Ranjit/odia_whisper_small_v3.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ranjit/odia_whisper_small_v3.0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Ranjit/odia_whisper_small_v3.0")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Ranjit/odia_whisper_small_v3.0") model = AutoModelForSpeechSeq2Seq.from_pretrained("Ranjit/odia_whisper_small_v3.0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from Ranjit/odia_whisper_small_v3.0: direct link, hf CLI and curl.
- Browser
- Download file 199 Bytes
-
https://huggingface.co/Ranjit/odia_whisper_small_v3.0/resolve/main/eval_results.json
- Command line
-
hf download hf://Ranjit/odia_whisper_small_v3.0/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/Ranjit/odia_whisper_small_v3.0/resolve/main/eval_results.json
199 Bytes
| { | |
| "epoch": 27.93, | |
| "eval_loss": 0.2584499418735504, | |
| "eval_runtime": 738.8296, | |
| "eval_samples_per_second": 9.396, | |
| "eval_steps_per_second": 0.294, | |
| "eval_wer": 13.861446892066024 | |
| } |