Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Italian
whisper
Generated from Trainer
whisper-event
Eval Results (legacy)
Instructions to use luigisaetta/whisper-tiny-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use luigisaetta/whisper-tiny-it with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="luigisaetta/whisper-tiny-it")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("luigisaetta/whisper-tiny-it") model = AutoModelForSpeechSeq2Seq.from_pretrained("luigisaetta/whisper-tiny-it", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
3216af7
1
Parent(s): 9dc323a
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,9 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the
|
| 23 |
Common Voice 11 dataset.
|
| 24 |
-
|
| 25 |
Language: Italian
|
| 26 |
-
|
| 27 |
It achieves the following results on the evaluation set:
|
| 28 |
- Loss: 0.3958
|
| 29 |
- Wer: 0.2661
|
|
|
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the
|
| 23 |
Common Voice 11 dataset.
|
|
|
|
| 24 |
Language: Italian
|
|
|
|
| 25 |
It achieves the following results on the evaluation set:
|
| 26 |
- Loss: 0.3958
|
| 27 |
- Wer: 0.2661
|