Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Polish
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use bardsai/whisper-small-pl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bardsai/whisper-small-pl with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="bardsai/whisper-small-pl")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("bardsai/whisper-small-pl") model = AutoModelForSpeechSeq2Seq.from_pretrained("bardsai/whisper-small-pl", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,16 +21,16 @@ model-index:
|
|
| 21 |
split: test
|
| 22 |
metrics:
|
| 23 |
- type: wer
|
| 24 |
-
value:
|
| 25 |
name: WER
|
| 26 |
- type: wer_without_norm
|
| 27 |
-
value:
|
| 28 |
name: WER unnormalized
|
| 29 |
- type: cer
|
| 30 |
-
value:
|
| 31 |
name: CER
|
| 32 |
- type: mer
|
| 33 |
-
value:
|
| 34 |
name: MER
|
| 35 |
---
|
| 36 |
|
|
|
|
| 21 |
split: test
|
| 22 |
metrics:
|
| 23 |
- type: wer
|
| 24 |
+
value: 14.57
|
| 25 |
name: WER
|
| 26 |
- type: wer_without_norm
|
| 27 |
+
value: 33.57
|
| 28 |
name: WER unnormalized
|
| 29 |
- type: cer
|
| 30 |
+
value: 4.02
|
| 31 |
name: CER
|
| 32 |
- type: mer
|
| 33 |
+
value: 14.37
|
| 34 |
name: MER
|
| 35 |
---
|
| 36 |
|