agnesluhtaru
commited on
Commit
•
6b2a443
1
Parent(s):
92b637f
update model card README.md
Browse files
README.md
CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [agnesluhtaru/whisper-large-et-ERR2020-v2](https://huggingface.co/agnesluhtaru/whisper-large-et-ERR2020-v2) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
-
- Wer: 15.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -45,21 +45,17 @@ The following hyperparameters were used during training:
|
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- lr_scheduler_warmup_steps: 200
|
48 |
-
- training_steps:
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.001 | 20.16 | 2500 | 0.3868 | 16.0356 |
|
60 |
-
| 0.0011 | 24.19 | 3000 | 0.3949 | 15.8293 |
|
61 |
-
| 0.0006 | 28.22 | 3500 | 0.4028 | 15.7476 |
|
62 |
-
| 0.0008 | 32.26 | 4000 | 0.4132 | 15.7347 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [agnesluhtaru/whisper-large-et-ERR2020-v2](https://huggingface.co/agnesluhtaru/whisper-large-et-ERR2020-v2) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.3934
|
20 |
+
- Wer: 15.6445
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- lr_scheduler_warmup_steps: 200
|
48 |
+
- training_steps: 2000
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
55 |
+
| 0.0302 | 4.03 | 500 | 0.2971 | 16.2892 |
|
56 |
+
| 0.0042 | 8.06 | 1000 | 0.3406 | 15.8551 |
|
57 |
+
| 0.0017 | 12.1 | 1500 | 0.3714 | 15.5585 |
|
58 |
+
| 0.0009 | 16.13 | 2000 | 0.3934 | 15.6445 |
|
|
|
|
|
|
|
|
|
59 |
|
60 |
|
61 |
### Framework versions
|