Model save
Browse files- README.md +21 -24
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +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 [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Wer:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -38,11 +38,9 @@ More information needed
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 1e-05
|
41 |
-
- train_batch_size:
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
44 |
-
- gradient_accumulation_steps: 2
|
45 |
-
- total_train_batch_size: 16
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- lr_scheduler_warmup_steps: 500
|
@@ -53,25 +51,24 @@ The following hyperparameters were used during training:
|
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
55 |
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.034 | 6.8670 | 1600 | 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.021 | 8.1545 | 1900 | 0.7722 | 40.9156 |
|
75 |
|
76 |
|
77 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.7130
|
21 |
+
- Wer: 43.1693
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 1e-05
|
41 |
+
- train_batch_size: 16
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
|
|
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 500
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
54 |
+
| 0.7784 | 0.4292 | 100 | 0.4158 | 34.8757 |
|
55 |
+
| 0.4942 | 0.8584 | 200 | 0.4306 | 33.8295 |
|
56 |
+
| 0.4017 | 1.2876 | 300 | 0.4313 | 38.3124 |
|
57 |
+
| 0.3677 | 1.7167 | 400 | 0.4539 | 39.1020 |
|
58 |
+
| 0.3498 | 2.1459 | 500 | 0.4611 | 41.6343 |
|
59 |
+
| 0.2632 | 2.5751 | 600 | 0.4645 | 37.8113 |
|
60 |
+
| 0.2701 | 3.0043 | 700 | 0.4461 | 37.3347 |
|
61 |
+
| 0.1499 | 3.4335 | 800 | 0.5147 | 40.4414 |
|
62 |
+
| 0.1596 | 3.8627 | 900 | 0.5218 | 41.5292 |
|
63 |
+
| 0.1073 | 4.2918 | 1000 | 0.5668 | 39.3977 |
|
64 |
+
| 0.0888 | 4.7210 | 1100 | 0.5665 | 39.4393 |
|
65 |
+
| 0.0738 | 5.1502 | 1200 | 0.6428 | 39.6104 |
|
66 |
+
| 0.0495 | 5.5794 | 1300 | 0.5914 | 41.9007 |
|
67 |
+
| 0.0512 | 6.0086 | 1400 | 0.6297 | 41.4950 |
|
68 |
+
| 0.0315 | 6.4378 | 1500 | 0.6753 | 44.4477 |
|
69 |
+
| 0.034 | 6.8670 | 1600 | 0.6906 | 38.4151 |
|
70 |
+
| 0.023 | 7.2961 | 1700 | 0.6998 | 40.0821 |
|
71 |
+
| 0.0251 | 7.7253 | 1800 | 0.7130 | 43.1693 |
|
|
|
72 |
|
73 |
|
74 |
### Framework versions
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4993448880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e71d35ef23d645c7da5179cc301233d49606c0ffafe616c37b754ad96141ef8
|
3 |
size 4993448880
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1180663192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b7b40a7d57652b513c0c486aab7f66a45299b31b44be9b8ecccfc26a795f5c2
|
3 |
size 1180663192
|