End of training
Browse files
README.md
CHANGED
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the zeroth_korean dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
-
- Cer:
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -47,14 +47,23 @@ The following hyperparameters were used during training:
|
|
47 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
48 |
- lr_scheduler_type: linear
|
49 |
- lr_scheduler_warmup_steps: 500
|
50 |
-
- training_steps:
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
-
| Training Loss | Epoch | Step
|
56 |
-
|
57 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the zeroth_korean dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.1870
|
24 |
+
- Cer: 9.5399
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
47 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
48 |
- lr_scheduler_type: linear
|
49 |
- lr_scheduler_warmup_steps: 500
|
50 |
+
- training_steps: 10000
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
56 |
+
|:-------------:|:------:|:-----:|:---------------:|:-------:|
|
57 |
+
| 0.4034 | 0.7184 | 1000 | 0.4414 | 14.7103 |
|
58 |
+
| 0.2432 | 1.4368 | 2000 | 0.3385 | 11.8208 |
|
59 |
+
| 0.1511 | 2.1552 | 3000 | 0.2778 | 9.6734 |
|
60 |
+
| 0.1295 | 2.8736 | 4000 | 0.2440 | 8.1855 |
|
61 |
+
| 0.0905 | 3.5920 | 5000 | 0.2219 | 7.8321 |
|
62 |
+
| 0.0638 | 4.3103 | 6000 | 0.2071 | 8.2915 |
|
63 |
+
| 0.0443 | 5.0287 | 7000 | 0.1970 | 9.0766 |
|
64 |
+
| 0.0534 | 5.7471 | 8000 | 0.1914 | 8.1069 |
|
65 |
+
| 0.0503 | 6.4655 | 9000 | 0.1879 | 6.7682 |
|
66 |
+
| 0.0308 | 7.1839 | 10000 | 0.1870 | 9.5399 |
|
67 |
|
68 |
|
69 |
### Framework versions
|
runs/Jul03_10-30-02_Airsound3/events.out.tfevents.1751506203.Airsound3.367215.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c5048e27ff8a9d1ca5c437901ba7b85a7b6a12872de93199266815ff06cb633
|
3 |
+
size 94630
|