Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Italian
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use ALM/whisper-it-small-augmented with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ALM/whisper-it-small-augmented with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ALM/whisper-it-small-augmented")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("ALM/whisper-it-small-augmented") model = AutoModelForSpeechSeq2Seq.from_pretrained("ALM/whisper-it-small-augmented", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from ALM/whisper-it-small-augmented: direct link, hf CLI and curl.
- Browser
- Download file 198 Bytes
-
https://huggingface.co/ALM/whisper-it-small-augmented/resolve/main/eval_results.json
- Command line
-
hf download hf://ALM/whisper-it-small-augmented/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/ALM/whisper-it-small-augmented/resolve/main/eval_results.json
198 Bytes
| { | |
| "epoch": 10.05, | |
| "eval_loss": 0.19797834753990173, | |
| "eval_runtime": 3138.908, | |
| "eval_samples_per_second": 4.78, | |
| "eval_steps_per_second": 0.149, | |
| "eval_wer": 8.745747395279608 | |
| } |