Hiro-nguyen
commited on
Commit
•
c17e695
1
Parent(s):
9b78ea2
End of training
Browse files- README.md +25 -4
- generation_config.json +74 -193
- model.safetensors +1 -1
README.md
CHANGED
@@ -2,10 +2,12 @@
|
|
2 |
language:
|
3 |
- en
|
4 |
license: apache-2.0
|
5 |
-
base_model: openai/whisper-base
|
6 |
tags:
|
7 |
- hf-asr-leaderboard
|
8 |
- generated_from_trainer
|
|
|
|
|
9 |
model-index:
|
10 |
- name: Whisper Base EN
|
11 |
results: []
|
@@ -16,7 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# Whisper Base EN
|
18 |
|
19 |
-
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the
|
|
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -36,14 +41,30 @@ More information needed
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 1e-05
|
39 |
-
- train_batch_size:
|
40 |
-
- eval_batch_size:
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
- lr_scheduler_warmup_steps: 500
|
45 |
- training_steps: 1000
|
46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
### Framework versions
|
48 |
|
49 |
- Transformers 4.38.0.dev0
|
|
|
2 |
language:
|
3 |
- en
|
4 |
license: apache-2.0
|
5 |
+
base_model: openai/whisper-base.en
|
6 |
tags:
|
7 |
- hf-asr-leaderboard
|
8 |
- generated_from_trainer
|
9 |
+
metrics:
|
10 |
+
- wer
|
11 |
model-index:
|
12 |
- name: Whisper Base EN
|
13 |
results: []
|
|
|
18 |
|
19 |
# Whisper Base EN
|
20 |
|
21 |
+
This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on the ADLINK dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0003
|
24 |
+
- Wer: 1.2422
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
- learning_rate: 1e-05
|
44 |
+
- train_batch_size: 8
|
45 |
+
- eval_batch_size: 8
|
46 |
- seed: 42
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
49 |
- lr_scheduler_warmup_steps: 500
|
50 |
- training_steps: 1000
|
51 |
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
55 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
56 |
+
| 1.4205 | 33.33 | 100 | 1.0960 | 9.9379 |
|
57 |
+
| 0.4057 | 66.67 | 200 | 0.3715 | 1.5528 |
|
58 |
+
| 0.0908 | 100.0 | 300 | 0.0704 | 1.5528 |
|
59 |
+
| 0.0053 | 133.33 | 400 | 0.0037 | 1.5528 |
|
60 |
+
| 0.0011 | 166.67 | 500 | 0.0010 | 1.2422 |
|
61 |
+
| 0.0006 | 200.0 | 600 | 0.0006 | 1.2422 |
|
62 |
+
| 0.0004 | 233.33 | 700 | 0.0004 | 1.2422 |
|
63 |
+
| 0.0003 | 266.67 | 800 | 0.0003 | 1.2422 |
|
64 |
+
| 0.0003 | 300.0 | 900 | 0.0003 | 1.2422 |
|
65 |
+
| 0.0003 | 333.33 | 1000 | 0.0003 | 1.2422 |
|
66 |
+
|
67 |
+
|
68 |
### Framework versions
|
69 |
|
70 |
- Transformers 4.38.0.dev0
|
generation_config.json
CHANGED
@@ -2,14 +2,6 @@
|
|
2 |
"alignment_heads": [
|
3 |
[
|
4 |
3,
|
5 |
-
1
|
6 |
-
],
|
7 |
-
[
|
8 |
-
4,
|
9 |
-
2
|
10 |
-
],
|
11 |
-
[
|
12 |
-
4,
|
13 |
3
|
14 |
],
|
15 |
[
|
@@ -22,141 +14,32 @@
|
|
22 |
],
|
23 |
[
|
24 |
5,
|
25 |
-
|
26 |
],
|
27 |
[
|
28 |
5,
|
29 |
-
|
30 |
-
],
|
31 |
-
[
|
32 |
-
5,
|
33 |
-
6
|
34 |
]
|
35 |
],
|
36 |
"begin_suppress_tokens": [
|
37 |
220,
|
38 |
-
|
39 |
],
|
40 |
"bos_token_id": 50257,
|
41 |
-
"decoder_start_token_id":
|
42 |
-
"eos_token_id":
|
43 |
"forced_decoder_ids": [
|
44 |
[
|
45 |
1,
|
46 |
-
|
47 |
-
],
|
48 |
-
[
|
49 |
-
2,
|
50 |
-
50359
|
51 |
]
|
52 |
],
|
53 |
-
"is_multilingual":
|
54 |
-
"lang_to_id": {
|
55 |
-
"<|af|>": 50327,
|
56 |
-
"<|am|>": 50334,
|
57 |
-
"<|ar|>": 50272,
|
58 |
-
"<|as|>": 50350,
|
59 |
-
"<|az|>": 50304,
|
60 |
-
"<|ba|>": 50355,
|
61 |
-
"<|be|>": 50330,
|
62 |
-
"<|bg|>": 50292,
|
63 |
-
"<|bn|>": 50302,
|
64 |
-
"<|bo|>": 50347,
|
65 |
-
"<|br|>": 50309,
|
66 |
-
"<|bs|>": 50315,
|
67 |
-
"<|ca|>": 50270,
|
68 |
-
"<|cs|>": 50283,
|
69 |
-
"<|cy|>": 50297,
|
70 |
-
"<|da|>": 50285,
|
71 |
-
"<|de|>": 50261,
|
72 |
-
"<|el|>": 50281,
|
73 |
-
"<|en|>": 50259,
|
74 |
-
"<|es|>": 50262,
|
75 |
-
"<|et|>": 50307,
|
76 |
-
"<|eu|>": 50310,
|
77 |
-
"<|fa|>": 50300,
|
78 |
-
"<|fi|>": 50277,
|
79 |
-
"<|fo|>": 50338,
|
80 |
-
"<|fr|>": 50265,
|
81 |
-
"<|gl|>": 50319,
|
82 |
-
"<|gu|>": 50333,
|
83 |
-
"<|haw|>": 50352,
|
84 |
-
"<|ha|>": 50354,
|
85 |
-
"<|he|>": 50279,
|
86 |
-
"<|hi|>": 50276,
|
87 |
-
"<|hr|>": 50291,
|
88 |
-
"<|ht|>": 50339,
|
89 |
-
"<|hu|>": 50286,
|
90 |
-
"<|hy|>": 50312,
|
91 |
-
"<|id|>": 50275,
|
92 |
-
"<|is|>": 50311,
|
93 |
-
"<|it|>": 50274,
|
94 |
-
"<|ja|>": 50266,
|
95 |
-
"<|jw|>": 50356,
|
96 |
-
"<|ka|>": 50329,
|
97 |
-
"<|kk|>": 50316,
|
98 |
-
"<|km|>": 50323,
|
99 |
-
"<|kn|>": 50306,
|
100 |
-
"<|ko|>": 50264,
|
101 |
-
"<|la|>": 50294,
|
102 |
-
"<|lb|>": 50345,
|
103 |
-
"<|ln|>": 50353,
|
104 |
-
"<|lo|>": 50336,
|
105 |
-
"<|lt|>": 50293,
|
106 |
-
"<|lv|>": 50301,
|
107 |
-
"<|mg|>": 50349,
|
108 |
-
"<|mi|>": 50295,
|
109 |
-
"<|mk|>": 50308,
|
110 |
-
"<|ml|>": 50296,
|
111 |
-
"<|mn|>": 50314,
|
112 |
-
"<|mr|>": 50320,
|
113 |
-
"<|ms|>": 50282,
|
114 |
-
"<|mt|>": 50343,
|
115 |
-
"<|my|>": 50346,
|
116 |
-
"<|ne|>": 50313,
|
117 |
-
"<|nl|>": 50271,
|
118 |
-
"<|nn|>": 50342,
|
119 |
-
"<|no|>": 50288,
|
120 |
-
"<|oc|>": 50328,
|
121 |
-
"<|pa|>": 50321,
|
122 |
-
"<|pl|>": 50269,
|
123 |
-
"<|ps|>": 50340,
|
124 |
-
"<|pt|>": 50267,
|
125 |
-
"<|ro|>": 50284,
|
126 |
-
"<|ru|>": 50263,
|
127 |
-
"<|sa|>": 50344,
|
128 |
-
"<|sd|>": 50332,
|
129 |
-
"<|si|>": 50322,
|
130 |
-
"<|sk|>": 50298,
|
131 |
-
"<|sl|>": 50305,
|
132 |
-
"<|sn|>": 50324,
|
133 |
-
"<|so|>": 50326,
|
134 |
-
"<|sq|>": 50317,
|
135 |
-
"<|sr|>": 50303,
|
136 |
-
"<|su|>": 50357,
|
137 |
-
"<|sv|>": 50273,
|
138 |
-
"<|sw|>": 50318,
|
139 |
-
"<|ta|>": 50287,
|
140 |
-
"<|te|>": 50299,
|
141 |
-
"<|tg|>": 50331,
|
142 |
-
"<|th|>": 50289,
|
143 |
-
"<|tk|>": 50341,
|
144 |
-
"<|tl|>": 50348,
|
145 |
-
"<|tr|>": 50268,
|
146 |
-
"<|tt|>": 50351,
|
147 |
-
"<|uk|>": 50280,
|
148 |
-
"<|ur|>": 50290,
|
149 |
-
"<|uz|>": 50337,
|
150 |
-
"<|vi|>": 50278,
|
151 |
-
"<|yi|>": 50335,
|
152 |
-
"<|yo|>": 50325,
|
153 |
-
"<|zh|>": 50260
|
154 |
-
},
|
155 |
"max_initial_timestamp_index": 50,
|
156 |
"max_length": 448,
|
157 |
-
"no_timestamps_token_id":
|
158 |
-
"pad_token_id":
|
159 |
-
"prev_sot_token_id":
|
160 |
"return_timestamps": false,
|
161 |
"suppress_tokens": [
|
162 |
1,
|
@@ -182,75 +65,73 @@
|
|
182 |
91,
|
183 |
92,
|
184 |
93,
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
-
|
198 |
-
|
199 |
-
|
200 |
-
|
201 |
-
|
202 |
-
|
203 |
-
|
204 |
-
|
205 |
-
|
206 |
-
|
207 |
-
|
208 |
-
|
209 |
-
|
210 |
-
|
211 |
-
|
212 |
-
|
213 |
-
|
214 |
-
|
215 |
-
|
216 |
-
|
217 |
-
|
218 |
-
|
219 |
-
|
220 |
-
|
221 |
-
|
222 |
-
|
223 |
-
|
224 |
-
|
225 |
-
|
226 |
-
|
227 |
-
|
228 |
-
|
229 |
-
|
230 |
-
|
231 |
-
|
232 |
-
|
233 |
-
|
234 |
-
|
235 |
-
|
236 |
-
|
237 |
-
|
238 |
-
|
239 |
-
|
240 |
-
|
241 |
-
|
242 |
-
|
243 |
-
|
244 |
-
|
|
|
|
|
|
|
245 |
50358,
|
246 |
50359,
|
247 |
50360,
|
248 |
-
50361
|
249 |
-
50362
|
250 |
],
|
251 |
-
"task_to_id": {
|
252 |
-
"transcribe": 50359,
|
253 |
-
"translate": 50358
|
254 |
-
},
|
255 |
"transformers_version": "4.38.0.dev0"
|
256 |
}
|
|
|
2 |
"alignment_heads": [
|
3 |
[
|
4 |
3,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
3
|
6 |
],
|
7 |
[
|
|
|
14 |
],
|
15 |
[
|
16 |
5,
|
17 |
+
5
|
18 |
],
|
19 |
[
|
20 |
5,
|
21 |
+
7
|
|
|
|
|
|
|
|
|
22 |
]
|
23 |
],
|
24 |
"begin_suppress_tokens": [
|
25 |
220,
|
26 |
+
50256
|
27 |
],
|
28 |
"bos_token_id": 50257,
|
29 |
+
"decoder_start_token_id": 50257,
|
30 |
+
"eos_token_id": 50256,
|
31 |
"forced_decoder_ids": [
|
32 |
[
|
33 |
1,
|
34 |
+
50362
|
|
|
|
|
|
|
|
|
35 |
]
|
36 |
],
|
37 |
+
"is_multilingual": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
"max_initial_timestamp_index": 50,
|
39 |
"max_length": 448,
|
40 |
+
"no_timestamps_token_id": 50362,
|
41 |
+
"pad_token_id": 50256,
|
42 |
+
"prev_sot_token_id": 50360,
|
43 |
"return_timestamps": false,
|
44 |
"suppress_tokens": [
|
45 |
1,
|
|
|
65 |
91,
|
66 |
92,
|
67 |
93,
|
68 |
+
357,
|
69 |
+
366,
|
70 |
+
438,
|
71 |
+
532,
|
72 |
+
685,
|
73 |
+
705,
|
74 |
+
796,
|
75 |
+
930,
|
76 |
+
1058,
|
77 |
+
1220,
|
78 |
+
1267,
|
79 |
+
1279,
|
80 |
+
1303,
|
81 |
+
1343,
|
82 |
+
1377,
|
83 |
+
1391,
|
84 |
+
1635,
|
85 |
+
1782,
|
86 |
+
1875,
|
87 |
+
2162,
|
88 |
+
2361,
|
89 |
+
2488,
|
90 |
+
3467,
|
91 |
+
4008,
|
92 |
+
4211,
|
93 |
+
4600,
|
94 |
+
4808,
|
95 |
+
5299,
|
96 |
+
5855,
|
97 |
+
6329,
|
98 |
+
7203,
|
99 |
+
9609,
|
100 |
+
9959,
|
101 |
+
10563,
|
102 |
+
10786,
|
103 |
+
11420,
|
104 |
+
11709,
|
105 |
+
11907,
|
106 |
+
13163,
|
107 |
+
13697,
|
108 |
+
13700,
|
109 |
+
14808,
|
110 |
+
15306,
|
111 |
+
16410,
|
112 |
+
16791,
|
113 |
+
17992,
|
114 |
+
19203,
|
115 |
+
19510,
|
116 |
+
20724,
|
117 |
+
22305,
|
118 |
+
22935,
|
119 |
+
27007,
|
120 |
+
30109,
|
121 |
+
30420,
|
122 |
+
33409,
|
123 |
+
34949,
|
124 |
+
40283,
|
125 |
+
40493,
|
126 |
+
40549,
|
127 |
+
47282,
|
128 |
+
49146,
|
129 |
+
50257,
|
130 |
+
50357,
|
131 |
50358,
|
132 |
50359,
|
133 |
50360,
|
134 |
+
50361
|
|
|
135 |
],
|
|
|
|
|
|
|
|
|
136 |
"transformers_version": "4.38.0.dev0"
|
137 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 290401888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe91f57490bd471d39f4532ce01f7a25d8440a23a111ab2a08d0ff87dd4d440b
|
3 |
size 290401888
|