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 metadata with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -32,6 +32,18 @@ model-index:
|
|
| 32 |
- type: mer
|
| 33 |
value: 14.37
|
| 34 |
name: MER
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
---
|
| 36 |
|
| 37 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
- type: mer
|
| 33 |
value: 14.37
|
| 34 |
name: MER
|
| 35 |
+
- task:
|
| 36 |
+
type: automatic-speech-recognition
|
| 37 |
+
name: Automatic Speech Recognition
|
| 38 |
+
dataset:
|
| 39 |
+
name: facebook/voxpopuli
|
| 40 |
+
type: facebook/voxpopuli
|
| 41 |
+
config: pl
|
| 42 |
+
split: test
|
| 43 |
+
metrics:
|
| 44 |
+
- type: wer
|
| 45 |
+
value: 15.73
|
| 46 |
+
name: WER
|
| 47 |
---
|
| 48 |
|
| 49 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|