Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Finnish
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use sgangireddy/whisper-medium-cv-fi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sgangireddy/whisper-medium-cv-fi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="sgangireddy/whisper-medium-cv-fi")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("sgangireddy/whisper-medium-cv-fi") model = AutoModelForSpeechSeq2Seq.from_pretrained("sgangireddy/whisper-medium-cv-fi") - Notebooks
- Google Colab
- Kaggle
Commit ·
c3636ca
1
Parent(s): fce38ee
Update README.md
Browse files
README.md
CHANGED
|
@@ -39,7 +39,11 @@ It achieves the following results on the evaluation set:
|
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
| 42 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
## Intended uses & limitations
|
| 45 |
|
|
|
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
| 42 |
+
The Model is fine-tuned for 1000 steps/updates on CV11 Finnish train+valiation data.
|
| 43 |
+
|
| 44 |
+
- Zero-shot - 18.8 (CV9 test data, even on CV11 the WER is closer a bit higher than this)
|
| 45 |
+
- Fine-tuned - 15.71 (CV11 test data)
|
| 46 |
+
|
| 47 |
|
| 48 |
## Intended uses & limitations
|
| 49 |
|