bayartsogt
commited on
Commit
•
6980865
1
Parent(s):
e93985d
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- wer
|
7 |
+
model-index:
|
8 |
+
- name: whisper-tiny-mn-9
|
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-tiny-mn-9
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.3885
|
20 |
+
- Wer: 45.5102
|
21 |
+
- Cer: 17.3377
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 1e-05
|
41 |
+
- train_batch_size: 64
|
42 |
+
- eval_batch_size: 64
|
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
|
47 |
+
- training_steps: 20000
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
|
54 |
+
| 0.587 | 0.69 | 1000 | 0.6937 | 75.6336 | 29.6764 |
|
55 |
+
| 0.4536 | 1.39 | 2000 | 0.5539 | 64.8187 | 24.8324 |
|
56 |
+
| 0.3798 | 2.08 | 3000 | 0.4963 | 57.7944 | 22.1842 |
|
57 |
+
| 0.3423 | 2.77 | 4000 | 0.4661 | 54.3751 | 20.9705 |
|
58 |
+
| 0.3122 | 3.47 | 5000 | 0.4449 | 52.5945 | 20.3405 |
|
59 |
+
| 0.3002 | 4.16 | 6000 | 0.4285 | 50.5080 | 19.3499 |
|
60 |
+
| 0.2842 | 4.85 | 7000 | 0.4171 | 49.3937 | 19.0282 |
|
61 |
+
| 0.2655 | 5.54 | 8000 | 0.4099 | 48.6727 | 18.6045 |
|
62 |
+
| 0.2555 | 6.24 | 9000 | 0.4035 | 48.2084 | 18.3392 |
|
63 |
+
| 0.2525 | 6.93 | 10000 | 0.3990 | 47.3290 | 17.8338 |
|
64 |
+
| 0.243 | 7.62 | 11000 | 0.3963 | 47.0559 | 18.2524 |
|
65 |
+
| 0.2358 | 8.32 | 12000 | 0.3948 | 46.7337 | 17.8186 |
|
66 |
+
| 0.2288 | 9.01 | 13000 | 0.3901 | 46.5480 | 17.9172 |
|
67 |
+
| 0.2171 | 9.7 | 14000 | 0.3910 | 46.0236 | 17.6266 |
|
68 |
+
| 0.2184 | 10.4 | 15000 | 0.3904 | 46.4387 | 17.8228 |
|
69 |
+
| 0.2099 | 11.09 | 16000 | 0.3893 | 45.9744 | 17.4379 |
|
70 |
+
| 0.216 | 11.78 | 17000 | 0.3889 | 45.6194 | 17.2939 |
|
71 |
+
| 0.2095 | 12.47 | 18000 | 0.3895 | 45.7887 | 17.4438 |
|
72 |
+
| 0.2056 | 13.17 | 19000 | 0.3882 | 45.6085 | 17.2888 |
|
73 |
+
| 0.2064 | 13.86 | 20000 | 0.3885 | 45.5102 | 17.3377 |
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.26.0.dev0
|
79 |
+
- Pytorch 1.13.0+cu117
|
80 |
+
- Datasets 2.7.1.dev0
|
81 |
+
- Tokenizers 0.13.2
|