Commit
•
9efeb6c
1
Parent(s):
461ff70
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- wer
|
7 |
+
model-index:
|
8 |
+
- name: whisper-synthesized-turkish-4-hour-llr
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# whisper-synthesized-turkish-4-hour-llr
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.2356
|
20 |
+
- Wer: 14.9179
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 1e-06
|
40 |
+
- train_batch_size: 16
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_steps: 500
|
46 |
+
- training_steps: 2000
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
53 |
+
| 1.8278 | 1.04 | 100 | 1.5357 | 41.2110 |
|
54 |
+
| 1.2048 | 2.08 | 200 | 0.8059 | 86.3165 |
|
55 |
+
| 0.6206 | 3.12 | 300 | 0.5751 | 94.1612 |
|
56 |
+
| 0.4927 | 4.17 | 400 | 0.5024 | 80.1568 |
|
57 |
+
| 0.4277 | 5.21 | 500 | 0.4451 | 48.6607 |
|
58 |
+
| 0.3502 | 6.25 | 600 | 0.3999 | 32.7490 |
|
59 |
+
| 0.2948 | 7.29 | 700 | 0.3650 | 21.5961 |
|
60 |
+
| 0.24 | 8.33 | 800 | 0.3344 | 17.7756 |
|
61 |
+
| 0.2079 | 9.38 | 900 | 0.3010 | 15.2512 |
|
62 |
+
| 0.1416 | 10.42 | 1000 | 0.2402 | 13.8687 |
|
63 |
+
| 0.1076 | 11.46 | 1100 | 0.2357 | 14.4427 |
|
64 |
+
| 0.0905 | 12.5 | 1200 | 0.2350 | 14.0415 |
|
65 |
+
| 0.0759 | 13.54 | 1300 | 0.2348 | 14.0230 |
|
66 |
+
| 0.0819 | 14.58 | 1400 | 0.2345 | 14.0600 |
|
67 |
+
| 0.0608 | 15.62 | 1500 | 0.2346 | 14.3563 |
|
68 |
+
| 0.0712 | 16.67 | 1600 | 0.2350 | 14.2575 |
|
69 |
+
| 0.0608 | 17.71 | 1700 | 0.2355 | 14.8562 |
|
70 |
+
| 0.0632 | 18.75 | 1800 | 0.2354 | 14.9241 |
|
71 |
+
| 0.0544 | 19.79 | 1900 | 0.2356 | 14.9303 |
|
72 |
+
| 0.0529 | 20.83 | 2000 | 0.2356 | 14.9179 |
|
73 |
+
|
74 |
+
|
75 |
+
### Framework versions
|
76 |
+
|
77 |
+
- Transformers 4.28.0
|
78 |
+
- Pytorch 2.0.0+cu118
|
79 |
+
- Datasets 2.11.0
|
80 |
+
- Tokenizers 0.13.3
|