Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Marathi
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use simran14/mr-val-g3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use simran14/mr-val-g3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="simran14/mr-val-g3")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("simran14/mr-val-g3") model = AutoModelForSpeechSeq2Seq.from_pretrained("simran14/mr-val-g3") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -66,11 +66,11 @@ The following hyperparameters were used during training:
|
|
| 66 |
|
| 67 |
### Training Results
|
| 68 |
|
| 69 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 70 |
-
|:-------------:|:-------:|:------:|:---------------:|:------:|
|
| 71 |
-
| 0.001 | 0.6098 | 1000 | 0.0017 | 0.
|
| 72 |
-
| 0.0006 | 1.2195 | 2000 | 0.0010 | 0.
|
| 73 |
-
| 0.0009 | 1.8293 | 3000 | 0.0008 | 0.
|
| 74 |
|
| 75 |
|
| 76 |
### Framework versions
|
|
|
|
| 66 |
|
| 67 |
### Training Results
|
| 68 |
|
| 69 |
+
| Training Loss | Epoch | Step | Validation Loss | WER |
|
| 70 |
+
|:-------------:|:-------:|:------:|:---------------:|:--------:|
|
| 71 |
+
| 0.001 | 0.6098 | 1000 | 0.0017 | 0.154740 |
|
| 72 |
+
| 0.0006 | 1.2195 | 2000 | 0.0010 | 0.126172 |
|
| 73 |
+
| 0.0009 | 1.8293 | 3000 | 0.0008 | 0.090463 |
|
| 74 |
|
| 75 |
|
| 76 |
### Framework versions
|