Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Greek
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use ALM/whisper-el-medium-augmented with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ALM/whisper-el-medium-augmented with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ALM/whisper-el-medium-augmented")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("ALM/whisper-el-medium-augmented") model = AutoModelForSpeechSeq2Seq.from_pretrained("ALM/whisper-el-medium-augmented") - Notebooks
- Google Colab
- Kaggle
Commit ·
2fdc19e
1
Parent(s): c5515c7
updated RREADME
Browse files
README.md
CHANGED
|
@@ -52,6 +52,14 @@ It achieves the following results on the evaluation set:
|
|
| 52 |
- Loss: 0.2807
|
| 53 |
- Wer: 17.7099
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
## Model description
|
| 56 |
|
| 57 |
More information needed
|
|
|
|
| 52 |
- Loss: 0.2807
|
| 53 |
- Wer: 17.7099
|
| 54 |
|
| 55 |
+
**IMPORTANT** The model has been trained using *data augmentation* to improve its generalization capabilities and robustness.
|
| 56 |
+
The results on the eval set during training are biased towards data augmentation applied to evaluation data.
|
| 57 |
+
|
| 58 |
+
**Results on eval set**
|
| 59 |
+
|
| 60 |
+
- Mozilla CV 11.0 - Greek: 13.250 WER (using official script)
|
| 61 |
+
- Google Fluers - Greek: 39.59 WER (using official script)
|
| 62 |
+
|
| 63 |
## Model description
|
| 64 |
|
| 65 |
More information needed
|