Commit
•
c5da1a0
1
Parent(s):
36e7d4a
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- wer
|
7 |
+
model-index:
|
8 |
+
- name: whisper-base-nl-3
|
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-base-nl-3
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.7927
|
20 |
+
- Wer: 31.4005
|
21 |
+
- Cer: 9.9570
|
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: 1
|
42 |
+
- eval_batch_size: 2
|
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: 5000
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
|
53 |
+
|:-------------:|:-----:|:-----:|:-------:|:---------------:|:-------:|
|
54 |
+
| 0.5761 | 0.06 | 1000 | 10.1154 | 0.5675 | 28.1532 |
|
55 |
+
| 0.48 | 0.13 | 2000 | 9.6911 | 0.5239 | 26.4364 |
|
56 |
+
| 0.4094 | 0.19 | 3000 | 9.1532 | 0.4925 | 24.8355 |
|
57 |
+
| 0.4792 | 0.26 | 4000 | 8.8414 | 0.4702 | 24.1105 |
|
58 |
+
| 0.3444 | 0.32 | 5000 | 8.8531 | 0.4544 | 23.9017 |
|
59 |
+
| 0.3943 | 0.39 | 6000 | 8.3602 | 0.4446 | 22.7353 |
|
60 |
+
| 0.4925 | 0.45 | 7000 | 8.3724 | 0.4348 | 22.1788 |
|
61 |
+
| 0.4455 | 0.52 | 8000 | 8.2989 | 0.4270 | 21.7549 |
|
62 |
+
| 0.3987 | 0.58 | 9000 | 7.9417 | 0.4139 | 20.8424 |
|
63 |
+
| 0.3373 | 0.65 | 10000 | 7.8871 | 0.4116 | 21.2144 |
|
64 |
+
| 0.3808 | 0.71 | 11000 | 7.6264 | 0.4016 | 20.5092 |
|
65 |
+
| 0.4214 | 0.78 | 12000 | 7.4153 | 0.3949 | 20.0938 |
|
66 |
+
| 0.3029 | 0.84 | 13000 | 7.3581 | 0.3902 | 19.7347 |
|
67 |
+
| 0.3549 | 1.66 | 14000 | 7.1195 | 0.3908 | 19.4115 |
|
68 |
+
| 0.3385 | 1.78 | 15000 | 7.7792 | 0.3906 | 20.2051 |
|
69 |
+
| 0.3282 | 1.9 | 16000 | 7.1081 | 0.3923 | 19.2651 |
|
70 |
+
| 0.3196 | 2.02 | 17000 | 7.2249 | 0.3923 | 19.3352 |
|
71 |
+
| 0.3251 | 2.14 | 18000 | 7.1761 | 0.3981 | 19.4831 |
|
72 |
+
| 0.4162 | 2.25 | 19000 | 7.0590 | 0.3958 | 19.0577 |
|
73 |
+
| 0.2851 | 2.37 | 20000 | 7.0167 | 0.3953 | 19.2095 |
|
74 |
+
| 0.2982 | 2.49 | 21000 | 6.8426 | 0.3929 | 18.8100 |
|
75 |
+
| 0.3642 | 2.61 | 22000 | 6.8867 | 0.3954 | 18.6972 |
|
76 |
+
| 0.2297 | 2.73 | 23000 | 6.9384 | 0.3916 | 18.7330 |
|
77 |
+
| 0.2313 | 2.85 | 24000 | 6.7785 | 0.3930 | 18.6034 |
|
78 |
+
| 0.2833 | 2.97 | 25000 | 6.8552 | 0.3910 | 18.5981 |
|
79 |
+
| 0.2509 | 3.09 | 26000 | 6.8165 | 0.3949 | 18.5180 |
|
80 |
+
| 0.2085 | 3.2 | 27000 | 6.8113 | 0.3985 | 18.6133 |
|
81 |
+
| 0.2055 | 3.32 | 28000 | 6.8624 | 0.3995 | 18.7612 |
|
82 |
+
| 0.175 | 3.44 | 29000 | 6.7727 | 0.4009 | 18.4814 |
|
83 |
+
| 0.1701 | 3.56 | 30000 | 7.0136 | 0.3998 | 18.8344 |
|
84 |
+
|
85 |
+
|
86 |
+
### Framework versions
|
87 |
+
|
88 |
+
- Transformers 4.26.0.dev0
|
89 |
+
- Pytorch 1.13.1+cu117
|
90 |
+
- Datasets 2.8.1.dev0
|
91 |
+
- Tokenizers 0.13.2
|