Commit
•
d1b6dd2
1
Parent(s):
a367437
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: openai/whisper-small
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- mozilla-foundation/fsc-audio-dataset
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
+
model-index:
|
11 |
+
- name: Personalized Whisper Small - Wei Fang
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
+
dataset:
|
17 |
+
name: fsc-audio-dataset
|
18 |
+
type: mozilla-foundation/fsc-audio-dataset
|
19 |
+
metrics:
|
20 |
+
- name: Wer
|
21 |
+
type: wer
|
22 |
+
value: 8.372290692732681
|
23 |
+
---
|
24 |
+
|
25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
26 |
+
should probably proofread and complete it, then remove this comment. -->
|
27 |
+
|
28 |
+
# Personalized Whisper Small - Wei Fang
|
29 |
+
|
30 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the fsc-audio-dataset dataset.
|
31 |
+
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 0.2946
|
33 |
+
- Wer: 8.3723
|
34 |
+
|
35 |
+
## Model description
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Intended uses & limitations
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training and evaluation data
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training procedure
|
48 |
+
|
49 |
+
### Training hyperparameters
|
50 |
+
|
51 |
+
The following hyperparameters were used during training:
|
52 |
+
- learning_rate: 1e-05
|
53 |
+
- train_batch_size: 32
|
54 |
+
- eval_batch_size: 8
|
55 |
+
- seed: 42
|
56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
+
- lr_scheduler_type: linear
|
58 |
+
- lr_scheduler_warmup_steps: 500
|
59 |
+
- training_steps: 4000
|
60 |
+
|
61 |
+
### Training results
|
62 |
+
|
63 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
64 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
65 |
+
| 0.9814 | 0.32 | 100 | 0.8164 | 13.2172 |
|
66 |
+
| 0.3013 | 0.64 | 200 | 0.2578 | 11.7722 |
|
67 |
+
| 0.2074 | 0.96 | 300 | 0.2192 | 10.4972 |
|
68 |
+
| 0.1429 | 1.28 | 400 | 0.2245 | 11.0072 |
|
69 |
+
| 0.1565 | 1.6 | 500 | 0.2102 | 10.6247 |
|
70 |
+
| 0.1554 | 1.92 | 600 | 0.2137 | 11.2197 |
|
71 |
+
| 0.0684 | 2.24 | 700 | 0.2139 | 8.8823 |
|
72 |
+
| 0.0717 | 2.56 | 800 | 0.2142 | 9.6898 |
|
73 |
+
| 0.0795 | 2.88 | 900 | 0.2128 | 9.2223 |
|
74 |
+
| 0.0329 | 3.21 | 1000 | 0.2341 | 9.3073 |
|
75 |
+
| 0.03 | 3.53 | 1100 | 0.2324 | 8.9673 |
|
76 |
+
| 0.0319 | 3.85 | 1200 | 0.2365 | 9.0948 |
|
77 |
+
| 0.0137 | 4.17 | 1300 | 0.2403 | 9.0523 |
|
78 |
+
| 0.0145 | 4.49 | 1400 | 0.2470 | 8.3723 |
|
79 |
+
| 0.0145 | 4.81 | 1500 | 0.2596 | 9.4348 |
|
80 |
+
| 0.0067 | 5.13 | 1600 | 0.2544 | 8.9248 |
|
81 |
+
| 0.0088 | 5.45 | 1700 | 0.2553 | 8.4573 |
|
82 |
+
| 0.0065 | 5.77 | 1800 | 0.2729 | 8.8823 |
|
83 |
+
| 0.0018 | 6.09 | 1900 | 0.2680 | 8.7973 |
|
84 |
+
| 0.0023 | 6.41 | 2000 | 0.2710 | 9.0948 |
|
85 |
+
| 0.0018 | 6.73 | 2100 | 0.2762 | 8.8398 |
|
86 |
+
| 0.002 | 7.05 | 2200 | 0.2717 | 8.5848 |
|
87 |
+
| 0.0011 | 7.37 | 2300 | 0.2784 | 8.5423 |
|
88 |
+
| 0.0012 | 7.69 | 2400 | 0.2797 | 8.4573 |
|
89 |
+
| 0.0011 | 8.01 | 2500 | 0.2782 | 8.3723 |
|
90 |
+
| 0.0007 | 8.33 | 2600 | 0.2838 | 8.1598 |
|
91 |
+
| 0.0007 | 8.65 | 2700 | 0.2826 | 8.2448 |
|
92 |
+
| 0.0013 | 8.97 | 2800 | 0.2835 | 8.4148 |
|
93 |
+
| 0.0006 | 9.29 | 2900 | 0.2913 | 8.2448 |
|
94 |
+
| 0.0006 | 9.62 | 3000 | 0.2906 | 8.4148 |
|
95 |
+
| 0.001 | 9.94 | 3100 | 0.2886 | 8.6273 |
|
96 |
+
| 0.0005 | 10.26 | 3200 | 0.2890 | 8.3723 |
|
97 |
+
| 0.0005 | 10.58 | 3300 | 0.2905 | 8.3723 |
|
98 |
+
| 0.0005 | 10.9 | 3400 | 0.2917 | 8.4573 |
|
99 |
+
| 0.0008 | 11.22 | 3500 | 0.2927 | 8.3723 |
|
100 |
+
| 0.0019 | 11.54 | 3600 | 0.2932 | 8.3723 |
|
101 |
+
| 0.0004 | 11.86 | 3700 | 0.2939 | 8.3723 |
|
102 |
+
| 0.0004 | 12.18 | 3800 | 0.2941 | 8.3723 |
|
103 |
+
| 0.0005 | 12.5 | 3900 | 0.2944 | 8.3723 |
|
104 |
+
| 0.0005 | 12.82 | 4000 | 0.2946 | 8.3723 |
|
105 |
+
|
106 |
+
|
107 |
+
### Framework versions
|
108 |
+
|
109 |
+
- Transformers 4.38.2
|
110 |
+
- Pytorch 2.2.1+cu121
|
111 |
+
- Datasets 2.18.0
|
112 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
@@ -0,0 +1,265 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"forced_decoder_ids": [
|
52 |
+
[
|
53 |
+
1,
|
54 |
+
null
|
55 |
+
],
|
56 |
+
[
|
57 |
+
2,
|
58 |
+
50359
|
59 |
+
]
|
60 |
+
],
|
61 |
+
"is_multilingual": true,
|
62 |
+
"lang_to_id": {
|
63 |
+
"<|af|>": 50327,
|
64 |
+
"<|am|>": 50334,
|
65 |
+
"<|ar|>": 50272,
|
66 |
+
"<|as|>": 50350,
|
67 |
+
"<|az|>": 50304,
|
68 |
+
"<|ba|>": 50355,
|
69 |
+
"<|be|>": 50330,
|
70 |
+
"<|bg|>": 50292,
|
71 |
+
"<|bn|>": 50302,
|
72 |
+
"<|bo|>": 50347,
|
73 |
+
"<|br|>": 50309,
|
74 |
+
"<|bs|>": 50315,
|
75 |
+
"<|ca|>": 50270,
|
76 |
+
"<|cs|>": 50283,
|
77 |
+
"<|cy|>": 50297,
|
78 |
+
"<|da|>": 50285,
|
79 |
+
"<|de|>": 50261,
|
80 |
+
"<|el|>": 50281,
|
81 |
+
"<|en|>": 50259,
|
82 |
+
"<|es|>": 50262,
|
83 |
+
"<|et|>": 50307,
|
84 |
+
"<|eu|>": 50310,
|
85 |
+
"<|fa|>": 50300,
|
86 |
+
"<|fi|>": 50277,
|
87 |
+
"<|fo|>": 50338,
|
88 |
+
"<|fr|>": 50265,
|
89 |
+
"<|gl|>": 50319,
|
90 |
+
"<|gu|>": 50333,
|
91 |
+
"<|haw|>": 50352,
|
92 |
+
"<|ha|>": 50354,
|
93 |
+
"<|he|>": 50279,
|
94 |
+
"<|hi|>": 50276,
|
95 |
+
"<|hr|>": 50291,
|
96 |
+
"<|ht|>": 50339,
|
97 |
+
"<|hu|>": 50286,
|
98 |
+
"<|hy|>": 50312,
|
99 |
+
"<|id|>": 50275,
|
100 |
+
"<|is|>": 50311,
|
101 |
+
"<|it|>": 50274,
|
102 |
+
"<|ja|>": 50266,
|
103 |
+
"<|jw|>": 50356,
|
104 |
+
"<|ka|>": 50329,
|
105 |
+
"<|kk|>": 50316,
|
106 |
+
"<|km|>": 50323,
|
107 |
+
"<|kn|>": 50306,
|
108 |
+
"<|ko|>": 50264,
|
109 |
+
"<|la|>": 50294,
|
110 |
+
"<|lb|>": 50345,
|
111 |
+
"<|ln|>": 50353,
|
112 |
+
"<|lo|>": 50336,
|
113 |
+
"<|lt|>": 50293,
|
114 |
+
"<|lv|>": 50301,
|
115 |
+
"<|mg|>": 50349,
|
116 |
+
"<|mi|>": 50295,
|
117 |
+
"<|mk|>": 50308,
|
118 |
+
"<|ml|>": 50296,
|
119 |
+
"<|mn|>": 50314,
|
120 |
+
"<|mr|>": 50320,
|
121 |
+
"<|ms|>": 50282,
|
122 |
+
"<|mt|>": 50343,
|
123 |
+
"<|my|>": 50346,
|
124 |
+
"<|ne|>": 50313,
|
125 |
+
"<|nl|>": 50271,
|
126 |
+
"<|nn|>": 50342,
|
127 |
+
"<|no|>": 50288,
|
128 |
+
"<|oc|>": 50328,
|
129 |
+
"<|pa|>": 50321,
|
130 |
+
"<|pl|>": 50269,
|
131 |
+
"<|ps|>": 50340,
|
132 |
+
"<|pt|>": 50267,
|
133 |
+
"<|ro|>": 50284,
|
134 |
+
"<|ru|>": 50263,
|
135 |
+
"<|sa|>": 50344,
|
136 |
+
"<|sd|>": 50332,
|
137 |
+
"<|si|>": 50322,
|
138 |
+
"<|sk|>": 50298,
|
139 |
+
"<|sl|>": 50305,
|
140 |
+
"<|sn|>": 50324,
|
141 |
+
"<|so|>": 50326,
|
142 |
+
"<|sq|>": 50317,
|
143 |
+
"<|sr|>": 50303,
|
144 |
+
"<|su|>": 50357,
|
145 |
+
"<|sv|>": 50273,
|
146 |
+
"<|sw|>": 50318,
|
147 |
+
"<|ta|>": 50287,
|
148 |
+
"<|te|>": 50299,
|
149 |
+
"<|tg|>": 50331,
|
150 |
+
"<|th|>": 50289,
|
151 |
+
"<|tk|>": 50341,
|
152 |
+
"<|tl|>": 50348,
|
153 |
+
"<|tr|>": 50268,
|
154 |
+
"<|tt|>": 50351,
|
155 |
+
"<|uk|>": 50280,
|
156 |
+
"<|ur|>": 50290,
|
157 |
+
"<|uz|>": 50337,
|
158 |
+
"<|vi|>": 50278,
|
159 |
+
"<|yi|>": 50335,
|
160 |
+
"<|yo|>": 50325,
|
161 |
+
"<|zh|>": 50260
|
162 |
+
},
|
163 |
+
"language": "mandarin",
|
164 |
+
"max_initial_timestamp_index": 50,
|
165 |
+
"max_length": 448,
|
166 |
+
"no_timestamps_token_id": 50363,
|
167 |
+
"pad_token_id": 50257,
|
168 |
+
"prev_sot_token_id": 50361,
|
169 |
+
"return_timestamps": false,
|
170 |
+
"suppress_tokens": [
|
171 |
+
1,
|
172 |
+
2,
|
173 |
+
7,
|
174 |
+
8,
|
175 |
+
9,
|
176 |
+
10,
|
177 |
+
14,
|
178 |
+
25,
|
179 |
+
26,
|
180 |
+
27,
|
181 |
+
28,
|
182 |
+
29,
|
183 |
+
31,
|
184 |
+
58,
|
185 |
+
59,
|
186 |
+
60,
|
187 |
+
61,
|
188 |
+
62,
|
189 |
+
63,
|
190 |
+
90,
|
191 |
+
91,
|
192 |
+
92,
|
193 |
+
93,
|
194 |
+
359,
|
195 |
+
503,
|
196 |
+
522,
|
197 |
+
542,
|
198 |
+
873,
|
199 |
+
893,
|
200 |
+
902,
|
201 |
+
918,
|
202 |
+
922,
|
203 |
+
931,
|
204 |
+
1350,
|
205 |
+
1853,
|
206 |
+
1982,
|
207 |
+
2460,
|
208 |
+
2627,
|
209 |
+
3246,
|
210 |
+
3253,
|
211 |
+
3268,
|
212 |
+
3536,
|
213 |
+
3846,
|
214 |
+
3961,
|
215 |
+
4183,
|
216 |
+
4667,
|
217 |
+
6585,
|
218 |
+
6647,
|
219 |
+
7273,
|
220 |
+
9061,
|
221 |
+
9383,
|
222 |
+
10428,
|
223 |
+
10929,
|
224 |
+
11938,
|
225 |
+
12033,
|
226 |
+
12331,
|
227 |
+
12562,
|
228 |
+
13793,
|
229 |
+
14157,
|
230 |
+
14635,
|
231 |
+
15265,
|
232 |
+
15618,
|
233 |
+
16553,
|
234 |
+
16604,
|
235 |
+
18362,
|
236 |
+
18956,
|
237 |
+
20075,
|
238 |
+
21675,
|
239 |
+
22520,
|
240 |
+
26130,
|
241 |
+
26161,
|
242 |
+
26435,
|
243 |
+
28279,
|
244 |
+
29464,
|
245 |
+
31650,
|
246 |
+
32302,
|
247 |
+
32470,
|
248 |
+
36865,
|
249 |
+
42863,
|
250 |
+
47425,
|
251 |
+
49870,
|
252 |
+
50254,
|
253 |
+
50258,
|
254 |
+
50358,
|
255 |
+
50359,
|
256 |
+
50360,
|
257 |
+
50361,
|
258 |
+
50362
|
259 |
+
],
|
260 |
+
"task_to_id": {
|
261 |
+
"transcribe": 50359,
|
262 |
+
"translate": 50358
|
263 |
+
},
|
264 |
+
"transformers_version": "4.38.2"
|
265 |
+
}
|
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 sha256:191479d7aa6b1f71bda8c5eb7953745aa08e7721eeb92fd5228f8ff829c71bb4
|
3 |
size 966995080
|
runs/Mar20_14-14-49_daniel0321/events.out.tfevents.1710915293.daniel0321.2677826.0
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:b326e597d79261ee561108ce789d89af863b7de5d791203189751c8369901003
|
3 |
+
size 52228
|