Rafaelrosendo1
commited on
Commit
•
9722fd5
1
Parent(s):
c1ced1a
Rafaelrosendo1/Large-v3
Browse files- README.md +5 -7
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [Rafaelrosendo1/whisper-large-pt](https://huggingface.co/Rafaelrosendo1/whisper-large-pt) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Wer: 23.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,7 +37,7 @@ More information needed
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
-
- learning_rate: 1e-
|
41 |
- train_batch_size: 32
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
@@ -46,15 +46,13 @@ The following hyperparameters were used during training:
|
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- lr_scheduler_warmup_steps: 1000
|
49 |
-
- training_steps:
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
55 |
-
| 0.0038 | 4
|
56 |
-
| 0.0021 | 9.51 | 4000 | 0.2568 | 23.1314 |
|
57 |
-
| 0.0023 | 14.27 | 6000 | 0.2627 | 23.2194 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [Rafaelrosendo1/whisper-large-pt](https://huggingface.co/Rafaelrosendo1/whisper-large-pt) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2494
|
21 |
+
- Wer: 23.0283
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 1e-08
|
41 |
- train_batch_size: 32
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
|
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- lr_scheduler_warmup_steps: 1000
|
49 |
+
- training_steps: 9000
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
55 |
+
| 0.0038 | 21.4 | 9000 | 0.2494 | 23.0283 |
|
|
|
|
|
56 |
|
57 |
|
58 |
### Framework versions
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6173656065
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e70e56c72d6febb91df6595d0f5fd2e1568e80b860ce97bf57e02ad008bca80d
|
3 |
size 6173656065
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3df7a02f698551974d7116af3389143d8dc01d20ee7b23716bb53d88c09eb85
|
3 |
size 4664
|