Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,10 @@ metrics:
|
|
| 10 |
model-index:
|
| 11 |
- name: whisper-large-v3-turbo-OpenSLR-GL
|
| 12 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -17,25 +21,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# whisper-large-v3-turbo-OpenSLR-GL
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
- Loss: 0.1613
|
| 23 |
-
- Wer:
|
| 24 |
-
- Bleu: 83.0952
|
| 25 |
-
|
| 26 |
-
## Model description
|
| 27 |
-
|
| 28 |
-
More information needed
|
| 29 |
-
|
| 30 |
-
## Intended uses & limitations
|
| 31 |
-
|
| 32 |
-
More information needed
|
| 33 |
-
|
| 34 |
-
## Training and evaluation data
|
| 35 |
-
|
| 36 |
-
More information needed
|
| 37 |
-
|
| 38 |
-
## Training procedure
|
| 39 |
|
| 40 |
### Training hyperparameters
|
| 41 |
|
|
@@ -55,18 +44,18 @@ The following hyperparameters were used during training:
|
|
| 55 |
|
| 56 |
### Training results
|
| 57 |
|
| 58 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 59 |
-
|
| 60 |
-
| 0.2739 | 1.0 | 75 | 0.1898 | 11.4023 |
|
| 61 |
-
| 0.1841 | 2.0 | 150 | 0.1819 | 10.3673 |
|
| 62 |
-
| 0.0542 | 3.0 | 225 | 0.1919 | 10.6177 |
|
| 63 |
-
| 0.0399 | 4.0 | 300 | 0.1934 | 11.1352 |
|
| 64 |
-
| 0.0264 | 5.0 | 375 | 0.2042 | 11.2688 |
|
| 65 |
-
| 0.0143 | 6.0 | 450 | 0.2075 | 10.3840 |
|
| 66 |
-
| 0.0056 | 7.0 | 525 | 0.2198 | 10.8347 |
|
| 67 |
-
| 0.0063 | 8.0 | 600 | 0.2217 | 10.9683 |
|
| 68 |
-
| 0.0037 | 9.0 | 675 | 0.2258 | 10.5509 |
|
| 69 |
-
| 0.0042 | 10.0 | 750 | 0.2278 | 10.6845 |
|
| 70 |
|
| 71 |
|
| 72 |
### Framework versions
|
|
@@ -74,4 +63,4 @@ The following hyperparameters were used during training:
|
|
| 74 |
- Transformers 4.47.1
|
| 75 |
- Pytorch 2.4.1+cu121
|
| 76 |
- Datasets 3.2.0
|
| 77 |
-
- Tokenizers 0.21.0
|
|
|
|
| 10 |
model-index:
|
| 11 |
- name: whisper-large-v3-turbo-OpenSLR-GL
|
| 12 |
results: []
|
| 13 |
+
datasets:
|
| 14 |
+
- juanjucm/OpenSLR-SpeechT-GL-EN
|
| 15 |
+
language:
|
| 16 |
+
- gl
|
| 17 |
---
|
| 18 |
|
| 19 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 21 |
|
| 22 |
# whisper-large-v3-turbo-OpenSLR-GL
|
| 23 |
|
| 24 |
+
This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on [juanjucm/OpenSLR-SpeechT-GL-EN](https://huggingface.co/datasets/juanjucm/OpenSLR-SpeechT-GL-EN).
|
| 25 |
It achieves the following results on the evaluation set:
|
| 26 |
- Loss: 0.1613
|
| 27 |
+
- Wer: 10.6845
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
### Training hyperparameters
|
| 30 |
|
|
|
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 49 |
+
| 0.2739 | 1.0 | 75 | 0.1898 | 11.4023 |
|
| 50 |
+
| 0.1841 | 2.0 | 150 | 0.1819 | 10.3673 |
|
| 51 |
+
| 0.0542 | 3.0 | 225 | 0.1919 | 10.6177 |
|
| 52 |
+
| 0.0399 | 4.0 | 300 | 0.1934 | 11.1352 |
|
| 53 |
+
| 0.0264 | 5.0 | 375 | 0.2042 | 11.2688 |
|
| 54 |
+
| 0.0143 | 6.0 | 450 | 0.2075 | 10.3840 |
|
| 55 |
+
| 0.0056 | 7.0 | 525 | 0.2198 | 10.8347 |
|
| 56 |
+
| 0.0063 | 8.0 | 600 | 0.2217 | 10.9683 |
|
| 57 |
+
| 0.0037 | 9.0 | 675 | 0.2258 | 10.5509 |
|
| 58 |
+
| 0.0042 | 10.0 | 750 | 0.2278 | 10.6845 |
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
|
|
|
| 63 |
- Transformers 4.47.1
|
| 64 |
- Pytorch 2.4.1+cu121
|
| 65 |
- Datasets 3.2.0
|
| 66 |
+
- Tokenizers 0.21.0
|