Commit
•
a174ad5
1
Parent(s):
edd511f
Model save
Browse files- README.md +67 -0
- generation_config.json +102 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- wer
|
6 |
+
model-index:
|
7 |
+
- name: quran-whisper-ar-tiny-1
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# quran-whisper-ar-tiny-1
|
15 |
+
|
16 |
+
This model was trained from scratch on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.5858
|
19 |
+
- Wer: 164.8352
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0001
|
39 |
+
- train_batch_size: 16
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- training_steps: 45
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
50 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
51 |
+
| 2.2643 | 0.3333 | 5 | 4.2666 | 209.8901 |
|
52 |
+
| 3.5798 | 0.6667 | 10 | 1.9318 | 173.6264 |
|
53 |
+
| 1.2993 | 1.0 | 15 | 1.0968 | 102.1978 |
|
54 |
+
| 0.8612 | 0.6667 | 20 | 0.9798 | 145.0549 |
|
55 |
+
| 0.7235 | 0.8333 | 25 | 0.7984 | 131.8681 |
|
56 |
+
| 0.5694 | 1.0 | 30 | 0.7010 | 127.4725 |
|
57 |
+
| 0.5781 | 0.7778 | 35 | 0.7017 | 378.0220 |
|
58 |
+
| 0.5704 | 0.8889 | 40 | 0.6511 | 341.7582 |
|
59 |
+
| 0.4247 | 1.0 | 45 | 0.5858 | 164.8352 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- Transformers 4.41.2
|
65 |
+
- Pytorch 2.1.2
|
66 |
+
- Datasets 2.19.2
|
67 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"begin_suppress_tokens": [
|
3 |
+
220,
|
4 |
+
50257
|
5 |
+
],
|
6 |
+
"bos_token_id": 50257,
|
7 |
+
"decoder_start_token_id": 50258,
|
8 |
+
"eos_token_id": 50257,
|
9 |
+
"max_length": 448,
|
10 |
+
"pad_token_id": 50257,
|
11 |
+
"suppress_tokens": [
|
12 |
+
1,
|
13 |
+
2,
|
14 |
+
7,
|
15 |
+
8,
|
16 |
+
9,
|
17 |
+
10,
|
18 |
+
14,
|
19 |
+
25,
|
20 |
+
26,
|
21 |
+
27,
|
22 |
+
28,
|
23 |
+
29,
|
24 |
+
31,
|
25 |
+
58,
|
26 |
+
59,
|
27 |
+
60,
|
28 |
+
61,
|
29 |
+
62,
|
30 |
+
63,
|
31 |
+
90,
|
32 |
+
91,
|
33 |
+
92,
|
34 |
+
93,
|
35 |
+
359,
|
36 |
+
503,
|
37 |
+
522,
|
38 |
+
542,
|
39 |
+
873,
|
40 |
+
893,
|
41 |
+
902,
|
42 |
+
918,
|
43 |
+
922,
|
44 |
+
931,
|
45 |
+
1350,
|
46 |
+
1853,
|
47 |
+
1982,
|
48 |
+
2460,
|
49 |
+
2627,
|
50 |
+
3246,
|
51 |
+
3253,
|
52 |
+
3268,
|
53 |
+
3536,
|
54 |
+
3846,
|
55 |
+
3961,
|
56 |
+
4183,
|
57 |
+
4667,
|
58 |
+
6585,
|
59 |
+
6647,
|
60 |
+
7273,
|
61 |
+
9061,
|
62 |
+
9383,
|
63 |
+
10428,
|
64 |
+
10929,
|
65 |
+
11938,
|
66 |
+
12033,
|
67 |
+
12331,
|
68 |
+
12562,
|
69 |
+
13793,
|
70 |
+
14157,
|
71 |
+
14635,
|
72 |
+
15265,
|
73 |
+
15618,
|
74 |
+
16553,
|
75 |
+
16604,
|
76 |
+
18362,
|
77 |
+
18956,
|
78 |
+
20075,
|
79 |
+
21675,
|
80 |
+
22520,
|
81 |
+
26130,
|
82 |
+
26161,
|
83 |
+
26435,
|
84 |
+
28279,
|
85 |
+
29464,
|
86 |
+
31650,
|
87 |
+
32302,
|
88 |
+
32470,
|
89 |
+
36865,
|
90 |
+
42863,
|
91 |
+
47425,
|
92 |
+
49870,
|
93 |
+
50254,
|
94 |
+
50258,
|
95 |
+
50358,
|
96 |
+
50359,
|
97 |
+
50360,
|
98 |
+
50361,
|
99 |
+
50362
|
100 |
+
],
|
101 |
+
"transformers_version": "4.41.2"
|
102 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151061672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:481139b035d68eeb280a27122f63d46fd007a33c2dfe5f7f6427c0e9dbcf6952
|
3 |
size 151061672
|