Update README.md
Browse files
README.md
CHANGED
@@ -17,11 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
# Whisper Tiny GA-EN Speech Translation
|
18 |
|
19 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
|
20 |
-
|
21 |
-
- Loss: 2.
|
22 |
-
- Bleu:
|
23 |
-
- Chrf: 32.
|
24 |
-
- Wer:
|
|
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -37,6 +38,10 @@ More information needed
|
|
37 |
|
38 |
## Training procedure
|
39 |
|
|
|
|
|
|
|
|
|
40 |
### Training hyperparameters
|
41 |
|
42 |
The following hyperparameters were used during training:
|
|
|
17 |
# Whisper Tiny GA-EN Speech Translation
|
18 |
|
19 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
|
20 |
+
The best model (this version) is at checkpoint 700, epoch 5.19, and it achieves the following results on the evaluation set:
|
21 |
+
- Loss: 2.7090
|
22 |
+
- Bleu: 17.56
|
23 |
+
- Chrf: 32.23
|
24 |
+
- Wer: 90.4998
|
25 |
+
|
26 |
|
27 |
## Model description
|
28 |
|
|
|
38 |
|
39 |
## Training procedure
|
40 |
|
41 |
+
### Experiment
|
42 |
+
|
43 |
+
Data Augmentation (processing)
|
44 |
+
|
45 |
### Training hyperparameters
|
46 |
|
47 |
The following hyperparameters were used during training:
|