KasuleTrevor
commited on
Commit
•
c555d30
1
Parent(s):
2755ccb
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
language:
|
4 |
+
- sw
|
5 |
+
license: apache-2.0
|
6 |
+
base_model: openai/whisper-small
|
7 |
+
tags:
|
8 |
+
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- mozilla-foundation/common_voice_18_0
|
11 |
+
metrics:
|
12 |
+
- wer
|
13 |
+
model-index:
|
14 |
+
- name: Whisper Small Hi - Sanchit Gandhi
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Automatic Speech Recognition
|
18 |
+
type: automatic-speech-recognition
|
19 |
+
dataset:
|
20 |
+
name: Common Voice 11.0
|
21 |
+
type: mozilla-foundation/common_voice_18_0
|
22 |
+
args: 'config: sw, split: test'
|
23 |
+
metrics:
|
24 |
+
- name: Wer
|
25 |
+
type: wer
|
26 |
+
value: 54.080058758722
|
27 |
+
---
|
28 |
+
|
29 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
30 |
+
should probably proofread and complete it, then remove this comment. -->
|
31 |
+
|
32 |
+
# Whisper Small Hi - Sanchit Gandhi
|
33 |
+
|
34 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
35 |
+
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 0.9542
|
37 |
+
- Wer: 54.0801
|
38 |
+
|
39 |
+
## Model description
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Intended uses & limitations
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training and evaluation data
|
48 |
+
|
49 |
+
More information needed
|
50 |
+
|
51 |
+
## Training procedure
|
52 |
+
|
53 |
+
### Training hyperparameters
|
54 |
+
|
55 |
+
The following hyperparameters were used during training:
|
56 |
+
- learning_rate: 1e-05
|
57 |
+
- train_batch_size: 16
|
58 |
+
- eval_batch_size: 8
|
59 |
+
- seed: 42
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- lr_scheduler_warmup_steps: 500
|
63 |
+
- training_steps: 5000
|
64 |
+
- mixed_precision_training: Native AMP
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
70 |
+
| 0.7988 | 0.2451 | 100 | 1.2849 | 109.6915 |
|
71 |
+
| 0.8952 | 0.4902 | 200 | 1.1418 | 95.3581 |
|
72 |
+
| 0.7785 | 0.7353 | 300 | 1.0263 | 94.3665 |
|
73 |
+
| 0.7053 | 0.9804 | 400 | 0.9466 | 85.3250 |
|
74 |
+
| 0.5318 | 1.2255 | 500 | 0.9058 | 81.4873 |
|
75 |
+
| 0.4995 | 1.4706 | 600 | 0.8554 | 66.8638 |
|
76 |
+
| 0.4802 | 1.7157 | 700 | 0.8245 | 64.1645 |
|
77 |
+
| 0.4654 | 1.9608 | 800 | 0.7959 | 77.4477 |
|
78 |
+
| 0.2461 | 2.2059 | 900 | 0.8013 | 66.1440 |
|
79 |
+
| 0.2342 | 2.4510 | 1000 | 0.7986 | 52.0676 |
|
80 |
+
| 0.2239 | 2.6961 | 1100 | 0.7772 | 62.4128 |
|
81 |
+
| 0.2732 | 2.9412 | 1200 | 0.7743 | 68.8065 |
|
82 |
+
| 0.1017 | 3.1863 | 1300 | 0.8005 | 65.6739 |
|
83 |
+
| 0.1081 | 3.4314 | 1400 | 0.8069 | 68.5678 |
|
84 |
+
| 0.1045 | 3.6765 | 1500 | 0.8008 | 63.2317 |
|
85 |
+
| 0.1076 | 3.9216 | 1600 | 0.7981 | 70.0220 |
|
86 |
+
| 0.0604 | 4.1667 | 1700 | 0.8220 | 57.7194 |
|
87 |
+
| 0.0449 | 4.4118 | 1800 | 0.8294 | 68.8652 |
|
88 |
+
| 0.0488 | 4.6569 | 1900 | 0.8347 | 59.0709 |
|
89 |
+
| 0.0453 | 4.9020 | 2000 | 0.8300 | 67.5468 |
|
90 |
+
| 0.0224 | 5.1471 | 2100 | 0.8509 | 51.2523 |
|
91 |
+
| 0.0179 | 5.3922 | 2200 | 0.8573 | 59.6071 |
|
92 |
+
| 0.0224 | 5.6373 | 2300 | 0.8622 | 50.2828 |
|
93 |
+
| 0.0218 | 5.8824 | 2400 | 0.8650 | 59.3720 |
|
94 |
+
| 0.01 | 6.1275 | 2500 | 0.8657 | 74.6126 |
|
95 |
+
| 0.0109 | 6.3725 | 2600 | 0.8816 | 64.8843 |
|
96 |
+
| 0.0095 | 6.6176 | 2700 | 0.8817 | 57.7378 |
|
97 |
+
| 0.0086 | 6.8627 | 2800 | 0.8824 | 69.1223 |
|
98 |
+
| 0.0046 | 7.1078 | 2900 | 0.8988 | 58.5861 |
|
99 |
+
| 0.0037 | 7.3529 | 3000 | 0.9064 | 55.1965 |
|
100 |
+
| 0.005 | 7.5980 | 3100 | 0.9079 | 65.3654 |
|
101 |
+
| 0.0048 | 7.8431 | 3200 | 0.8993 | 52.4128 |
|
102 |
+
| 0.0023 | 8.0882 | 3300 | 0.9158 | 59.9412 |
|
103 |
+
| 0.0021 | 8.3333 | 3400 | 0.9183 | 55.7363 |
|
104 |
+
| 0.0022 | 8.5784 | 3500 | 0.9247 | 60.8336 |
|
105 |
+
| 0.002 | 8.8235 | 3600 | 0.9282 | 60.2644 |
|
106 |
+
| 0.0017 | 9.0686 | 3700 | 0.9243 | 61.2156 |
|
107 |
+
| 0.0016 | 9.3137 | 3800 | 0.9308 | 61.0797 |
|
108 |
+
| 0.0017 | 9.5588 | 3900 | 0.9399 | 52.4091 |
|
109 |
+
| 0.0014 | 9.8039 | 4000 | 0.9414 | 50.3783 |
|
110 |
+
| 0.0013 | 10.0490 | 4100 | 0.9440 | 54.8109 |
|
111 |
+
| 0.0013 | 10.2941 | 4200 | 0.9430 | 58.0353 |
|
112 |
+
| 0.0013 | 10.5392 | 4300 | 0.9472 | 55.0790 |
|
113 |
+
| 0.0012 | 10.7843 | 4400 | 0.9470 | 55.8538 |
|
114 |
+
| 0.0011 | 11.0294 | 4500 | 0.9488 | 56.8454 |
|
115 |
+
| 0.0011 | 11.2745 | 4600 | 0.9517 | 54.1315 |
|
116 |
+
| 0.0011 | 11.5196 | 4700 | 0.9530 | 53.8414 |
|
117 |
+
| 0.0011 | 11.7647 | 4800 | 0.9538 | 54.4583 |
|
118 |
+
| 0.0011 | 12.0098 | 4900 | 0.9539 | 54.0507 |
|
119 |
+
| 0.0011 | 12.2549 | 5000 | 0.9542 | 54.0801 |
|
120 |
+
|
121 |
+
|
122 |
+
### Framework versions
|
123 |
+
|
124 |
+
- Transformers 4.44.2
|
125 |
+
- Pytorch 2.1.0+cu118
|
126 |
+
- Datasets 2.21.0
|
127 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alignment_heads": [
|
3 |
+
[
|
4 |
+
5,
|
5 |
+
3
|
6 |
+
],
|
7 |
+
[
|
8 |
+
5,
|
9 |
+
9
|
10 |
+
],
|
11 |
+
[
|
12 |
+
8,
|
13 |
+
0
|
14 |
+
],
|
15 |
+
[
|
16 |
+
8,
|
17 |
+
4
|
18 |
+
],
|
19 |
+
[
|
20 |
+
8,
|
21 |
+
7
|
22 |
+
],
|
23 |
+
[
|
24 |
+
8,
|
25 |
+
8
|
26 |
+
],
|
27 |
+
[
|
28 |
+
9,
|
29 |
+
0
|
30 |
+
],
|
31 |
+
[
|
32 |
+
9,
|
33 |
+
7
|
34 |
+
],
|
35 |
+
[
|
36 |
+
9,
|
37 |
+
9
|
38 |
+
],
|
39 |
+
[
|
40 |
+
10,
|
41 |
+
5
|
42 |
+
]
|
43 |
+
],
|
44 |
+
"begin_suppress_tokens": [
|
45 |
+
220,
|
46 |
+
50257
|
47 |
+
],
|
48 |
+
"bos_token_id": 50257,
|
49 |
+
"decoder_start_token_id": 50258,
|
50 |
+
"eos_token_id": 50257,
|
51 |
+
"is_multilingual": true,
|
52 |
+
"lang_to_id": {
|
53 |
+
"<|af|>": 50327,
|
54 |
+
"<|am|>": 50334,
|
55 |
+
"<|ar|>": 50272,
|
56 |
+
"<|as|>": 50350,
|
57 |
+
"<|az|>": 50304,
|
58 |
+
"<|ba|>": 50355,
|
59 |
+
"<|be|>": 50330,
|
60 |
+
"<|bg|>": 50292,
|
61 |
+
"<|bn|>": 50302,
|
62 |
+
"<|bo|>": 50347,
|
63 |
+
"<|br|>": 50309,
|
64 |
+
"<|bs|>": 50315,
|
65 |
+
"<|ca|>": 50270,
|
66 |
+
"<|cs|>": 50283,
|
67 |
+
"<|cy|>": 50297,
|
68 |
+
"<|da|>": 50285,
|
69 |
+
"<|de|>": 50261,
|
70 |
+
"<|el|>": 50281,
|
71 |
+
"<|en|>": 50259,
|
72 |
+
"<|es|>": 50262,
|
73 |
+
"<|et|>": 50307,
|
74 |
+
"<|eu|>": 50310,
|
75 |
+
"<|fa|>": 50300,
|
76 |
+
"<|fi|>": 50277,
|
77 |
+
"<|fo|>": 50338,
|
78 |
+
"<|fr|>": 50265,
|
79 |
+
"<|gl|>": 50319,
|
80 |
+
"<|gu|>": 50333,
|
81 |
+
"<|haw|>": 50352,
|
82 |
+
"<|ha|>": 50354,
|
83 |
+
"<|he|>": 50279,
|
84 |
+
"<|hi|>": 50276,
|
85 |
+
"<|hr|>": 50291,
|
86 |
+
"<|ht|>": 50339,
|
87 |
+
"<|hu|>": 50286,
|
88 |
+
"<|hy|>": 50312,
|
89 |
+
"<|id|>": 50275,
|
90 |
+
"<|is|>": 50311,
|
91 |
+
"<|it|>": 50274,
|
92 |
+
"<|ja|>": 50266,
|
93 |
+
"<|jw|>": 50356,
|
94 |
+
"<|ka|>": 50329,
|
95 |
+
"<|kk|>": 50316,
|
96 |
+
"<|km|>": 50323,
|
97 |
+
"<|kn|>": 50306,
|
98 |
+
"<|ko|>": 50264,
|
99 |
+
"<|la|>": 50294,
|
100 |
+
"<|lb|>": 50345,
|
101 |
+
"<|ln|>": 50353,
|
102 |
+
"<|lo|>": 50336,
|
103 |
+
"<|lt|>": 50293,
|
104 |
+
"<|lv|>": 50301,
|
105 |
+
"<|mg|>": 50349,
|
106 |
+
"<|mi|>": 50295,
|
107 |
+
"<|mk|>": 50308,
|
108 |
+
"<|ml|>": 50296,
|
109 |
+
"<|mn|>": 50314,
|
110 |
+
"<|mr|>": 50320,
|
111 |
+
"<|ms|>": 50282,
|
112 |
+
"<|mt|>": 50343,
|
113 |
+
"<|my|>": 50346,
|
114 |
+
"<|ne|>": 50313,
|
115 |
+
"<|nl|>": 50271,
|
116 |
+
"<|nn|>": 50342,
|
117 |
+
"<|no|>": 50288,
|
118 |
+
"<|oc|>": 50328,
|
119 |
+
"<|pa|>": 50321,
|
120 |
+
"<|pl|>": 50269,
|
121 |
+
"<|ps|>": 50340,
|
122 |
+
"<|pt|>": 50267,
|
123 |
+
"<|ro|>": 50284,
|
124 |
+
"<|ru|>": 50263,
|
125 |
+
"<|sa|>": 50344,
|
126 |
+
"<|sd|>": 50332,
|
127 |
+
"<|si|>": 50322,
|
128 |
+
"<|sk|>": 50298,
|
129 |
+
"<|sl|>": 50305,
|
130 |
+
"<|sn|>": 50324,
|
131 |
+
"<|so|>": 50326,
|
132 |
+
"<|sq|>": 50317,
|
133 |
+
"<|sr|>": 50303,
|
134 |
+
"<|su|>": 50357,
|
135 |
+
"<|sv|>": 50273,
|
136 |
+
"<|sw|>": 50318,
|
137 |
+
"<|ta|>": 50287,
|
138 |
+
"<|te|>": 50299,
|
139 |
+
"<|tg|>": 50331,
|
140 |
+
"<|th|>": 50289,
|
141 |
+
"<|tk|>": 50341,
|
142 |
+
"<|tl|>": 50348,
|
143 |
+
"<|tr|>": 50268,
|
144 |
+
"<|tt|>": 50351,
|
145 |
+
"<|uk|>": 50280,
|
146 |
+
"<|ur|>": 50290,
|
147 |
+
"<|uz|>": 50337,
|
148 |
+
"<|vi|>": 50278,
|
149 |
+
"<|yi|>": 50335,
|
150 |
+
"<|yo|>": 50325,
|
151 |
+
"<|zh|>": 50260
|
152 |
+
},
|
153 |
+
"language": "english",
|
154 |
+
"max_initial_timestamp_index": 50,
|
155 |
+
"max_length": 448,
|
156 |
+
"no_timestamps_token_id": 50363,
|
157 |
+
"pad_token_id": 50257,
|
158 |
+
"prev_sot_token_id": 50361,
|
159 |
+
"return_timestamps": false,
|
160 |
+
"suppress_tokens": [
|
161 |
+
1,
|
162 |
+
2,
|
163 |
+
7,
|
164 |
+
8,
|
165 |
+
9,
|
166 |
+
10,
|
167 |
+
14,
|
168 |
+
25,
|
169 |
+
26,
|
170 |
+
27,
|
171 |
+
28,
|
172 |
+
29,
|
173 |
+
31,
|
174 |
+
58,
|
175 |
+
59,
|
176 |
+
60,
|
177 |
+
61,
|
178 |
+
62,
|
179 |
+
63,
|
180 |
+
90,
|
181 |
+
91,
|
182 |
+
92,
|
183 |
+
93,
|
184 |
+
359,
|
185 |
+
503,
|
186 |
+
522,
|
187 |
+
542,
|
188 |
+
873,
|
189 |
+
893,
|
190 |
+
902,
|
191 |
+
918,
|
192 |
+
922,
|
193 |
+
931,
|
194 |
+
1350,
|
195 |
+
1853,
|
196 |
+
1982,
|
197 |
+
2460,
|
198 |
+
2627,
|
199 |
+
3246,
|
200 |
+
3253,
|
201 |
+
3268,
|
202 |
+
3536,
|
203 |
+
3846,
|
204 |
+
3961,
|
205 |
+
4183,
|
206 |
+
4667,
|
207 |
+
6585,
|
208 |
+
6647,
|
209 |
+
7273,
|
210 |
+
9061,
|
211 |
+
9383,
|
212 |
+
10428,
|
213 |
+
10929,
|
214 |
+
11938,
|
215 |
+
12033,
|
216 |
+
12331,
|
217 |
+
12562,
|
218 |
+
13793,
|
219 |
+
14157,
|
220 |
+
14635,
|
221 |
+
15265,
|
222 |
+
15618,
|
223 |
+
16553,
|
224 |
+
16604,
|
225 |
+
18362,
|
226 |
+
18956,
|
227 |
+
20075,
|
228 |
+
21675,
|
229 |
+
22520,
|
230 |
+
26130,
|
231 |
+
26161,
|
232 |
+
26435,
|
233 |
+
28279,
|
234 |
+
29464,
|
235 |
+
31650,
|
236 |
+
32302,
|
237 |
+
32470,
|
238 |
+
36865,
|
239 |
+
42863,
|
240 |
+
47425,
|
241 |
+
49870,
|
242 |
+
50254,
|
243 |
+
50258,
|
244 |
+
50358,
|
245 |
+
50359,
|
246 |
+
50360,
|
247 |
+
50361,
|
248 |
+
50362
|
249 |
+
],
|
250 |
+
"task": "transcribe",
|
251 |
+
"task_to_id": {
|
252 |
+
"transcribe": 50359,
|
253 |
+
"translate": 50358
|
254 |
+
},
|
255 |
+
"transformers_version": "4.44.2"
|
256 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f22205a2041af053e1de0e82ecae608731bc0f0b011a8c95d123fbc4ece3c82
|
3 |
size 966995080
|
runs/Sep07_17-46-37_1f6a75bc0c50/events.out.tfevents.1725731206.1f6a75bc0c50.772.3
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:e6a119155e93938ea51c97ef74837c76995272687566435636eb0a19ca0ab153
|
3 |
+
size 65112
|