Update README.md
Browse files
README.md
CHANGED
|
@@ -40,18 +40,25 @@ It achieves the following results on the evaluation set:
|
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
| 43 |
-
|
|
|
|
| 44 |
|
| 45 |
## Intended uses & limitations
|
| 46 |
|
| 47 |
-
|
| 48 |
|
| 49 |
## Training and evaluation data
|
| 50 |
|
| 51 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
|
| 53 |
## Training procedure
|
| 54 |
|
|
|
|
|
|
|
| 55 |
### Training hyperparameters
|
| 56 |
|
| 57 |
The following hyperparameters were used during training:
|
|
|
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
| 43 |
+
The model was developed during the Whisper Fine-Tuning Event in December 2022.
|
| 44 |
+
More details on the model can be found [in the original paper](https://cdn.openai.com/papers/whisper.pdf)
|
| 45 |
|
| 46 |
## Intended uses & limitations
|
| 47 |
|
| 48 |
+
The model is fine-tuned for transcription in the Greek language.
|
| 49 |
|
| 50 |
## Training and evaluation data
|
| 51 |
|
| 52 |
+
This model was trained by interleaving the training and evaluation splits from two different datasets:
|
| 53 |
+
|
| 54 |
+
- mozilla-foundation/common_voice_11_0 (el)
|
| 55 |
+
- google/fleurs (el_gr)
|
| 56 |
+
|
| 57 |
|
| 58 |
## Training procedure
|
| 59 |
|
| 60 |
+
The python script used is a modified version of the script provided by Hugging Face and can be found [here](https://github.com/kamfonas/whisper-fine-tuning-event/blob/minor-mods-by-farsipal/run_speech_recognition_seq2seq_streaming.py)
|
| 61 |
+
|
| 62 |
### Training hyperparameters
|
| 63 |
|
| 64 |
The following hyperparameters were used during training:
|