End of training
Browse files
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: apache-2.0
|
5 |
+
base_model: openai/whisper-small
|
6 |
+
tags:
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- Jzuluaga/atcosim_corpus
|
10 |
+
metrics:
|
11 |
+
- wer
|
12 |
+
model-index:
|
13 |
+
- name: Whisper Base ATCOSIM
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Automatic Speech Recognition
|
17 |
+
type: automatic-speech-recognition
|
18 |
+
dataset:
|
19 |
+
name: atcosim_corpus_numbers_converted
|
20 |
+
type: Jzuluaga/atcosim_corpus
|
21 |
+
args: 'config: en, split: test'
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 404.9337012855893
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# Whisper Base ATCOSIM
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the atcosim_corpus_numbers_converted dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.5964
|
36 |
+
- Wer: 404.9337
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 1e-05
|
56 |
+
- train_batch_size: 16
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- lr_scheduler_warmup_steps: 500
|
62 |
+
- training_steps: 1000
|
63 |
+
- mixed_precision_training: Native AMP
|
64 |
+
|
65 |
+
### Training results
|
66 |
+
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
68 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
69 |
+
| 8.7316 | 0.2092 | 100 | 8.1521 | 110.7020 |
|
70 |
+
| 5.3768 | 0.4184 | 200 | 5.2758 | 110.9713 |
|
71 |
+
| 3.2842 | 0.6276 | 300 | 3.4243 | 119.1492 |
|
72 |
+
| 1.892 | 0.8368 | 400 | 2.1743 | 121.4377 |
|
73 |
+
| 0.9999 | 1.0460 | 500 | 1.4513 | 168.8160 |
|
74 |
+
| 0.6472 | 1.2552 | 600 | 1.0157 | 369.7449 |
|
75 |
+
| 0.529 | 1.4644 | 700 | 0.8372 | 356.8554 |
|
76 |
+
| 0.4086 | 1.6736 | 800 | 0.6973 | 300.4644 |
|
77 |
+
| 0.3559 | 1.8828 | 900 | 0.6164 | 361.0150 |
|
78 |
+
| 0.2302 | 2.0921 | 1000 | 0.5964 | 404.9337 |
|
79 |
+
|
80 |
+
|
81 |
+
### Framework versions
|
82 |
+
|
83 |
+
- Transformers 4.42.0.dev0
|
84 |
+
- Pytorch 2.3.0+cu121
|
85 |
+
- Datasets 2.19.2
|
86 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alignment_heads": [
|
3 |
+
[
|
4 |
+
6,
|
5 |
+
6
|
6 |
+
],
|
7 |
+
[
|
8 |
+
7,
|
9 |
+
0
|
10 |
+
],
|
11 |
+
[
|
12 |
+
7,
|
13 |
+
3
|
14 |
+
],
|
15 |
+
[
|
16 |
+
7,
|
17 |
+
8
|
18 |
+
],
|
19 |
+
[
|
20 |
+
8,
|
21 |
+
2
|
22 |
+
],
|
23 |
+
[
|
24 |
+
8,
|
25 |
+
5
|
26 |
+
],
|
27 |
+
[
|
28 |
+
8,
|
29 |
+
7
|
30 |
+
],
|
31 |
+
[
|
32 |
+
9,
|
33 |
+
0
|
34 |
+
],
|
35 |
+
[
|
36 |
+
9,
|
37 |
+
4
|
38 |
+
],
|
39 |
+
[
|
40 |
+
9,
|
41 |
+
8
|
42 |
+
],
|
43 |
+
[
|
44 |
+
9,
|
45 |
+
10
|
46 |
+
],
|
47 |
+
[
|
48 |
+
10,
|
49 |
+
0
|
50 |
+
],
|
51 |
+
[
|
52 |
+
10,
|
53 |
+
1
|
54 |
+
],
|
55 |
+
[
|
56 |
+
10,
|
57 |
+
2
|
58 |
+
],
|
59 |
+
[
|
60 |
+
10,
|
61 |
+
3
|
62 |
+
],
|
63 |
+
[
|
64 |
+
10,
|
65 |
+
6
|
66 |
+
],
|
67 |
+
[
|
68 |
+
10,
|
69 |
+
11
|
70 |
+
],
|
71 |
+
[
|
72 |
+
11,
|
73 |
+
2
|
74 |
+
],
|
75 |
+
[
|
76 |
+
11,
|
77 |
+
4
|
78 |
+
]
|
79 |
+
],
|
80 |
+
"begin_suppress_tokens": [
|
81 |
+
220,
|
82 |
+
50256
|
83 |
+
],
|
84 |
+
"bos_token_id": 50257,
|
85 |
+
"decoder_start_token_id": 50257,
|
86 |
+
"eos_token_id": 50256,
|
87 |
+
"forced_decoder_ids": [
|
88 |
+
[
|
89 |
+
1,
|
90 |
+
50362
|
91 |
+
]
|
92 |
+
],
|
93 |
+
"is_multilingual": false,
|
94 |
+
"max_initial_timestamp_index": 50,
|
95 |
+
"max_length": 448,
|
96 |
+
"no_timestamps_token_id": 50362,
|
97 |
+
"pad_token_id": 50256,
|
98 |
+
"prev_sot_token_id": 50360,
|
99 |
+
"suppress_tokens": [
|
100 |
+
1,
|
101 |
+
2,
|
102 |
+
7,
|
103 |
+
8,
|
104 |
+
9,
|
105 |
+
10,
|
106 |
+
14,
|
107 |
+
25,
|
108 |
+
26,
|
109 |
+
27,
|
110 |
+
28,
|
111 |
+
29,
|
112 |
+
31,
|
113 |
+
58,
|
114 |
+
59,
|
115 |
+
60,
|
116 |
+
61,
|
117 |
+
62,
|
118 |
+
63,
|
119 |
+
90,
|
120 |
+
91,
|
121 |
+
92,
|
122 |
+
93,
|
123 |
+
357,
|
124 |
+
366,
|
125 |
+
438,
|
126 |
+
532,
|
127 |
+
685,
|
128 |
+
705,
|
129 |
+
796,
|
130 |
+
930,
|
131 |
+
1058,
|
132 |
+
1220,
|
133 |
+
1267,
|
134 |
+
1279,
|
135 |
+
1303,
|
136 |
+
1343,
|
137 |
+
1377,
|
138 |
+
1391,
|
139 |
+
1635,
|
140 |
+
1782,
|
141 |
+
1875,
|
142 |
+
2162,
|
143 |
+
2361,
|
144 |
+
2488,
|
145 |
+
3467,
|
146 |
+
4008,
|
147 |
+
4211,
|
148 |
+
4600,
|
149 |
+
4808,
|
150 |
+
5299,
|
151 |
+
5855,
|
152 |
+
6329,
|
153 |
+
7203,
|
154 |
+
9609,
|
155 |
+
9959,
|
156 |
+
10563,
|
157 |
+
10786,
|
158 |
+
11420,
|
159 |
+
11709,
|
160 |
+
11907,
|
161 |
+
13163,
|
162 |
+
13697,
|
163 |
+
13700,
|
164 |
+
14808,
|
165 |
+
15306,
|
166 |
+
16410,
|
167 |
+
16791,
|
168 |
+
17992,
|
169 |
+
19203,
|
170 |
+
19510,
|
171 |
+
20724,
|
172 |
+
22305,
|
173 |
+
22935,
|
174 |
+
27007,
|
175 |
+
30109,
|
176 |
+
30420,
|
177 |
+
33409,
|
178 |
+
34949,
|
179 |
+
40283,
|
180 |
+
40493,
|
181 |
+
40549,
|
182 |
+
47282,
|
183 |
+
49146,
|
184 |
+
50257,
|
185 |
+
50357,
|
186 |
+
50358,
|
187 |
+
50359,
|
188 |
+
50360,
|
189 |
+
50361
|
190 |
+
],
|
191 |
+
"transformers_version": "4.42.0.dev0"
|
192 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966992008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51589097502b3611fc455b5cc64b5c09e63e15803b286195b4bbab98e683ec7c
|
3 |
size 966992008
|
runs/Jun11_14-07-58_af17497d9b7e/events.out.tfevents.1718114879.af17497d9b7e.143.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b204bee02f31b59a8cae063bf01926fc18e1d3817bc82f1345a33ebea25c3f5a
|
3 |
+
size 17688
|