Update README.md
Browse files
README.md
CHANGED
|
@@ -32,25 +32,29 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
# Whisper Small - Greek (el)
|
| 34 |
|
| 35 |
-
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the mozilla-foundation/common_voice_11_0 el dataset
|
|
|
|
| 36 |
It achieves the following results on the evaluation set:
|
| 37 |
- Loss: 0.4642
|
| 38 |
- Wer: 25.6965
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
| 42 |
-
|
| 43 |
|
| 44 |
## Intended uses & limitations
|
| 45 |
|
| 46 |
-
|
| 47 |
|
| 48 |
## Training and evaluation data
|
| 49 |
|
| 50 |
-
|
|
|
|
| 51 |
|
| 52 |
## Training procedure
|
| 53 |
|
|
|
|
|
|
|
| 54 |
### Training hyperparameters
|
| 55 |
|
| 56 |
The following hyperparameters were used during training:
|
|
|
|
| 32 |
|
| 33 |
# Whisper Small - Greek (el)
|
| 34 |
|
| 35 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the mozilla-foundation/common_voice_11_0 el dataset
|
| 36 |
+
for translation from Greek to English.
|
| 37 |
It achieves the following results on the evaluation set:
|
| 38 |
- Loss: 0.4642
|
| 39 |
- Wer: 25.6965
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
| 43 |
+
This model was finetuned with the encoder frozen. Only the decoder weights have been changed by this training run.
|
| 44 |
|
| 45 |
## Intended uses & limitations
|
| 46 |
|
| 47 |
+
The purpose of this model was to understand how the freezing of a part of the model might affect learning, in an effort to assess the feasibility of enabling adapters.
|
| 48 |
|
| 49 |
## Training and evaluation data
|
| 50 |
|
| 51 |
+
The training was performed by streaming interleaved train+eval spits of the greek (el) subset of mozilla-foundation/common_voice_11_0 (el).
|
| 52 |
+
The test set was similarly used for validation.
|
| 53 |
|
| 54 |
## Training procedure
|
| 55 |
|
| 56 |
+
The script used to perform the training is included in the files of this space:
|
| 57 |
+
|
| 58 |
### Training hyperparameters
|
| 59 |
|
| 60 |
The following hyperparameters were used during training:
|