Update README.md
Browse filesAdded the training Jupyter notebook.
README.md
CHANGED
|
@@ -21,23 +21,25 @@ This model is a fine-tuned version of [facebook/wav2vec2-large-960h](https://hug
|
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
|
| 23 |
WER: 0.262
|
|
|
|
| 24 |
CER: 0.126
|
| 25 |
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
## Intended uses & limitations
|
| 32 |
|
| 33 |
-
More information needed
|
| 34 |
|
| 35 |
## Training and evaluation data
|
| 36 |
|
| 37 |
-
|
|
|
|
| 38 |
|
| 39 |
## Training procedure
|
| 40 |
|
|
|
|
|
|
|
|
|
|
| 41 |
### Training hyperparameters
|
| 42 |
|
| 43 |
The following hyperparameters were used during training:
|
|
|
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
|
| 23 |
WER: 0.262
|
| 24 |
+
|
| 25 |
CER: 0.126
|
| 26 |
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
| 30 |
+
This is a voice-2-text transcription model specialized for the acc dataset.
|
|
|
|
|
|
|
| 31 |
|
|
|
|
| 32 |
|
| 33 |
## Training and evaluation data
|
| 34 |
|
| 35 |
+
Training was based on the training set in [acc_dataset_v2](https://huggingface.co/datasets/monadical-labs/acc_dataset_v2) and evaluation based on
|
| 36 |
+
the validation and test sets in the same dataset.
|
| 37 |
|
| 38 |
## Training procedure
|
| 39 |
|
| 40 |
+
See the Jupyter notebook [Finetuning-notebook-wav2vec2-large-960h-on-acc-data](https://huggingface.co/ilokavat/wav2vec2-large-960h/blob/main/Finetuning-notebook-wav2vec2-large-960h-on-acc-data.ipynb)
|
| 41 |
+
for the full training procedure.
|
| 42 |
+
|
| 43 |
### Training hyperparameters
|
| 44 |
|
| 45 |
The following hyperparameters were used during training:
|