akera commited on
Commit
d6a0a6d
·
1 Parent(s): f70aa6b

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +290 -0
README.md ADDED
@@ -0,0 +1,290 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: facebook/mms-1b-all
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: mms-lug
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # mms-lug
17
+
18
+ This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: inf
21
+ - Wer: 0.1745
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.001
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 100
47
+ - num_epochs: 5
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | No log | 0.02 | 20 | inf | 1.0049 |
54
+ | No log | 0.04 | 40 | inf | 1.0 |
55
+ | No log | 0.07 | 60 | inf | 0.3009 |
56
+ | No log | 0.09 | 80 | inf | 0.1998 |
57
+ | 4.042 | 0.11 | 100 | inf | 0.2110 |
58
+ | 4.042 | 0.13 | 120 | inf | 0.2047 |
59
+ | 4.042 | 0.15 | 140 | inf | 0.2040 |
60
+ | 4.042 | 0.17 | 160 | inf | 0.1949 |
61
+ | 4.042 | 0.2 | 180 | inf | 0.2026 |
62
+ | 0.3406 | 0.22 | 200 | inf | 0.1833 |
63
+ | 0.3406 | 0.24 | 220 | inf | 0.1875 |
64
+ | 0.3406 | 0.26 | 240 | inf | 0.2128 |
65
+ | 0.3406 | 0.28 | 260 | inf | 0.1910 |
66
+ | 0.3406 | 0.3 | 280 | inf | 0.1798 |
67
+ | 0.2831 | 0.33 | 300 | inf | 0.1749 |
68
+ | 0.2831 | 0.35 | 320 | inf | 0.1875 |
69
+ | 0.2831 | 0.37 | 340 | inf | 0.1780 |
70
+ | 0.2831 | 0.39 | 360 | inf | 0.1907 |
71
+ | 0.2831 | 0.41 | 380 | inf | 0.2005 |
72
+ | 0.2796 | 0.43 | 400 | inf | 0.2037 |
73
+ | 0.2796 | 0.46 | 420 | inf | 0.1973 |
74
+ | 0.2796 | 0.48 | 440 | inf | 0.1917 |
75
+ | 0.2796 | 0.5 | 460 | inf | 0.2015 |
76
+ | 0.2796 | 0.52 | 480 | inf | 0.1784 |
77
+ | 0.3198 | 0.54 | 500 | inf | 0.1812 |
78
+ | 0.3198 | 0.56 | 520 | inf | 0.1808 |
79
+ | 0.3198 | 0.59 | 540 | inf | 0.1987 |
80
+ | 0.3198 | 0.61 | 560 | inf | 0.1696 |
81
+ | 0.3198 | 0.63 | 580 | inf | 0.1710 |
82
+ | 0.3131 | 0.65 | 600 | inf | 0.1794 |
83
+ | 0.3131 | 0.67 | 620 | inf | 0.1773 |
84
+ | 0.3131 | 0.69 | 640 | inf | 0.1777 |
85
+ | 0.3131 | 0.72 | 660 | inf | 0.2005 |
86
+ | 0.3131 | 0.74 | 680 | inf | 0.1886 |
87
+ | 0.2777 | 0.76 | 700 | inf | 0.2058 |
88
+ | 0.2777 | 0.78 | 720 | inf | 0.1770 |
89
+ | 0.2777 | 0.8 | 740 | inf | 0.1801 |
90
+ | 0.2777 | 0.83 | 760 | inf | 0.1914 |
91
+ | 0.2777 | 0.85 | 780 | inf | 0.1770 |
92
+ | 0.2694 | 0.87 | 800 | inf | 0.1815 |
93
+ | 0.2694 | 0.89 | 820 | inf | 0.1717 |
94
+ | 0.2694 | 0.91 | 840 | inf | 0.1777 |
95
+ | 0.2694 | 0.93 | 860 | inf | 0.1671 |
96
+ | 0.2694 | 0.96 | 880 | inf | 0.1706 |
97
+ | 0.3216 | 0.98 | 900 | inf | 0.2381 |
98
+ | 0.3216 | 1.0 | 920 | inf | 0.1766 |
99
+ | 0.3216 | 1.02 | 940 | inf | 0.1826 |
100
+ | 0.3216 | 1.04 | 960 | inf | 0.1749 |
101
+ | 0.3216 | 1.06 | 980 | inf | 0.1836 |
102
+ | 0.3008 | 1.09 | 1000 | inf | 0.1696 |
103
+ | 0.3008 | 1.11 | 1020 | inf | 0.1703 |
104
+ | 0.3008 | 1.13 | 1040 | inf | 0.1703 |
105
+ | 0.3008 | 1.15 | 1060 | inf | 0.1942 |
106
+ | 0.3008 | 1.17 | 1080 | inf | 0.1780 |
107
+ | 0.2621 | 1.19 | 1100 | inf | 0.1626 |
108
+ | 0.2621 | 1.22 | 1120 | inf | 0.1728 |
109
+ | 0.2621 | 1.24 | 1140 | inf | 0.1738 |
110
+ | 0.2621 | 1.26 | 1160 | inf | 0.1745 |
111
+ | 0.2621 | 1.28 | 1180 | inf | 0.1766 |
112
+ | 0.2837 | 1.3 | 1200 | inf | 0.1685 |
113
+ | 0.2837 | 1.32 | 1220 | inf | 0.1647 |
114
+ | 0.2837 | 1.35 | 1240 | inf | 0.1664 |
115
+ | 0.2837 | 1.37 | 1260 | inf | 0.1784 |
116
+ | 0.2837 | 1.39 | 1280 | inf | 0.1699 |
117
+ | 0.2648 | 1.41 | 1300 | inf | 0.1713 |
118
+ | 0.2648 | 1.43 | 1320 | inf | 0.1749 |
119
+ | 0.2648 | 1.45 | 1340 | inf | 0.1692 |
120
+ | 0.2648 | 1.48 | 1360 | inf | 0.1808 |
121
+ | 0.2648 | 1.5 | 1380 | inf | 0.1724 |
122
+ | 0.3012 | 1.52 | 1400 | inf | 0.1710 |
123
+ | 0.3012 | 1.54 | 1420 | inf | 0.1668 |
124
+ | 0.3012 | 1.56 | 1440 | inf | 0.1724 |
125
+ | 0.3012 | 1.59 | 1460 | inf | 0.1763 |
126
+ | 0.3012 | 1.61 | 1480 | inf | 0.1868 |
127
+ | 0.287 | 1.63 | 1500 | inf | 0.1675 |
128
+ | 0.287 | 1.65 | 1520 | inf | 0.1728 |
129
+ | 0.287 | 1.67 | 1540 | inf | 0.1661 |
130
+ | 0.287 | 1.69 | 1560 | inf | 0.1657 |
131
+ | 0.287 | 1.72 | 1580 | inf | 0.1794 |
132
+ | 0.2042 | 1.74 | 1600 | inf | 0.1685 |
133
+ | 0.2042 | 1.76 | 1620 | inf | 0.1956 |
134
+ | 0.2042 | 1.78 | 1640 | inf | 0.1594 |
135
+ | 0.2042 | 1.8 | 1660 | inf | 0.1626 |
136
+ | 0.2042 | 1.82 | 1680 | inf | 0.1559 |
137
+ | 0.3219 | 1.85 | 1700 | inf | 0.1612 |
138
+ | 0.3219 | 1.87 | 1720 | inf | 0.1759 |
139
+ | 0.3219 | 1.89 | 1740 | inf | 0.1742 |
140
+ | 0.3219 | 1.91 | 1760 | inf | 0.1738 |
141
+ | 0.3219 | 1.93 | 1780 | inf | 0.1640 |
142
+ | 0.2695 | 1.95 | 1800 | inf | 0.1678 |
143
+ | 0.2695 | 1.98 | 1820 | inf | 0.1615 |
144
+ | 0.2695 | 2.0 | 1840 | inf | 0.1685 |
145
+ | 0.2695 | 2.02 | 1860 | inf | 0.1650 |
146
+ | 0.2695 | 2.04 | 1880 | inf | 0.1682 |
147
+ | 0.2759 | 2.06 | 1900 | inf | 0.1938 |
148
+ | 0.2759 | 2.08 | 1920 | inf | 0.1629 |
149
+ | 0.2759 | 2.11 | 1940 | inf | 0.1587 |
150
+ | 0.2759 | 2.13 | 1960 | inf | 0.1566 |
151
+ | 0.2759 | 2.15 | 1980 | inf | 0.1605 |
152
+ | 0.2584 | 2.17 | 2000 | inf | 0.1699 |
153
+ | 0.2584 | 2.19 | 2020 | inf | 0.1780 |
154
+ | 0.2584 | 2.21 | 2040 | inf | 0.1664 |
155
+ | 0.2584 | 2.24 | 2060 | inf | 0.1629 |
156
+ | 0.2584 | 2.26 | 2080 | inf | 0.1699 |
157
+ | 0.2618 | 2.28 | 2100 | inf | 0.1629 |
158
+ | 0.2618 | 2.3 | 2120 | inf | 0.1692 |
159
+ | 0.2618 | 2.32 | 2140 | inf | 0.1706 |
160
+ | 0.2618 | 2.35 | 2160 | inf | 0.1675 |
161
+ | 0.2618 | 2.37 | 2180 | inf | 0.1696 |
162
+ | 0.278 | 2.39 | 2200 | inf | 0.1626 |
163
+ | 0.278 | 2.41 | 2220 | inf | 0.1612 |
164
+ | 0.278 | 2.43 | 2240 | inf | 0.1696 |
165
+ | 0.278 | 2.45 | 2260 | inf | 0.1654 |
166
+ | 0.278 | 2.48 | 2280 | inf | 0.1668 |
167
+ | 0.2213 | 2.5 | 2300 | inf | 0.1678 |
168
+ | 0.2213 | 2.52 | 2320 | inf | 0.1745 |
169
+ | 0.2213 | 2.54 | 2340 | inf | 0.1640 |
170
+ | 0.2213 | 2.56 | 2360 | inf | 0.1608 |
171
+ | 0.2213 | 2.58 | 2380 | inf | 0.1573 |
172
+ | 0.2187 | 2.61 | 2400 | inf | 0.1657 |
173
+ | 0.2187 | 2.63 | 2420 | inf | 0.1587 |
174
+ | 0.2187 | 2.65 | 2440 | inf | 0.1622 |
175
+ | 0.2187 | 2.67 | 2460 | inf | 0.1717 |
176
+ | 0.2187 | 2.69 | 2480 | inf | 0.1562 |
177
+ | 0.2585 | 2.71 | 2500 | inf | 0.1573 |
178
+ | 0.2585 | 2.74 | 2520 | inf | 0.1566 |
179
+ | 0.2585 | 2.76 | 2540 | inf | 0.1742 |
180
+ | 0.2585 | 2.78 | 2560 | inf | 0.1605 |
181
+ | 0.2585 | 2.8 | 2580 | inf | 0.1605 |
182
+ | 0.2913 | 2.82 | 2600 | inf | 0.1745 |
183
+ | 0.2913 | 2.84 | 2620 | inf | 0.1608 |
184
+ | 0.2913 | 2.87 | 2640 | inf | 0.1615 |
185
+ | 0.2913 | 2.89 | 2660 | inf | 0.1675 |
186
+ | 0.2913 | 2.91 | 2680 | inf | 0.1612 |
187
+ | 0.2743 | 2.93 | 2700 | inf | 0.1577 |
188
+ | 0.2743 | 2.95 | 2720 | inf | 0.1598 |
189
+ | 0.2743 | 2.98 | 2740 | inf | 0.1566 |
190
+ | 0.2743 | 3.0 | 2760 | inf | 0.1573 |
191
+ | 0.2743 | 3.02 | 2780 | inf | 0.1594 |
192
+ | 0.2854 | 3.04 | 2800 | inf | 0.1608 |
193
+ | 0.2854 | 3.06 | 2820 | inf | 0.1650 |
194
+ | 0.2854 | 3.08 | 2840 | inf | 0.1580 |
195
+ | 0.2854 | 3.11 | 2860 | inf | 0.1640 |
196
+ | 0.2854 | 3.13 | 2880 | inf | 0.1594 |
197
+ | 0.243 | 3.15 | 2900 | inf | 0.1601 |
198
+ | 0.243 | 3.17 | 2920 | inf | 0.1703 |
199
+ | 0.243 | 3.19 | 2940 | inf | 0.1573 |
200
+ | 0.243 | 3.21 | 2960 | inf | 0.1587 |
201
+ | 0.243 | 3.24 | 2980 | inf | 0.1668 |
202
+ | 0.2563 | 3.26 | 3000 | inf | 0.1713 |
203
+ | 0.2563 | 3.28 | 3020 | inf | 0.1570 |
204
+ | 0.2563 | 3.3 | 3040 | inf | 0.1601 |
205
+ | 0.2563 | 3.32 | 3060 | inf | 0.1619 |
206
+ | 0.2563 | 3.34 | 3080 | inf | 0.1541 |
207
+ | 0.228 | 3.37 | 3100 | inf | 0.1552 |
208
+ | 0.228 | 3.39 | 3120 | inf | 0.1566 |
209
+ | 0.228 | 3.41 | 3140 | inf | 0.1552 |
210
+ | 0.228 | 3.43 | 3160 | inf | 0.1619 |
211
+ | 0.228 | 3.45 | 3180 | inf | 0.1657 |
212
+ | 0.2684 | 3.47 | 3200 | inf | 0.1622 |
213
+ | 0.2684 | 3.5 | 3220 | inf | 0.1548 |
214
+ | 0.2684 | 3.52 | 3240 | inf | 0.1608 |
215
+ | 0.2684 | 3.54 | 3260 | inf | 0.1664 |
216
+ | 0.2684 | 3.56 | 3280 | inf | 0.1594 |
217
+ | 0.2623 | 3.58 | 3300 | inf | 0.1650 |
218
+ | 0.2623 | 3.6 | 3320 | inf | 0.1541 |
219
+ | 0.2623 | 3.63 | 3340 | inf | 0.1555 |
220
+ | 0.2623 | 3.65 | 3360 | inf | 0.1598 |
221
+ | 0.2623 | 3.67 | 3380 | inf | 0.1629 |
222
+ | 0.2573 | 3.69 | 3400 | inf | 0.1584 |
223
+ | 0.2573 | 3.71 | 3420 | inf | 0.1650 |
224
+ | 0.2573 | 3.74 | 3440 | inf | 0.1612 |
225
+ | 0.2573 | 3.76 | 3460 | inf | 0.1615 |
226
+ | 0.2573 | 3.78 | 3480 | inf | 0.1584 |
227
+ | 0.2698 | 3.8 | 3500 | inf | 0.1591 |
228
+ | 0.2698 | 3.82 | 3520 | inf | 0.1601 |
229
+ | 0.2698 | 3.84 | 3540 | inf | 0.1626 |
230
+ | 0.2698 | 3.87 | 3560 | inf | 0.1566 |
231
+ | 0.2698 | 3.89 | 3580 | inf | 0.1699 |
232
+ | 0.2178 | 3.91 | 3600 | inf | 0.1647 |
233
+ | 0.2178 | 3.93 | 3620 | inf | 0.1608 |
234
+ | 0.2178 | 3.95 | 3640 | inf | 0.1703 |
235
+ | 0.2178 | 3.97 | 3660 | inf | 0.1717 |
236
+ | 0.2178 | 4.0 | 3680 | inf | 0.1626 |
237
+ | 0.2964 | 4.02 | 3700 | inf | 0.1612 |
238
+ | 0.2964 | 4.04 | 3720 | inf | 0.1671 |
239
+ | 0.2964 | 4.06 | 3740 | inf | 0.1682 |
240
+ | 0.2964 | 4.08 | 3760 | inf | 0.1738 |
241
+ | 0.2964 | 4.1 | 3780 | inf | 0.1728 |
242
+ | 0.2778 | 4.13 | 3800 | inf | 0.1879 |
243
+ | 0.2778 | 4.15 | 3820 | inf | 0.1633 |
244
+ | 0.2778 | 4.17 | 3840 | inf | 0.1675 |
245
+ | 0.2778 | 4.19 | 3860 | inf | 0.1657 |
246
+ | 0.2778 | 4.21 | 3880 | inf | 0.1879 |
247
+ | 0.292 | 4.23 | 3900 | inf | 0.1664 |
248
+ | 0.292 | 4.26 | 3920 | inf | 0.1699 |
249
+ | 0.292 | 4.28 | 3940 | inf | 0.1822 |
250
+ | 0.292 | 4.3 | 3960 | inf | 0.1678 |
251
+ | 0.292 | 4.32 | 3980 | inf | 0.1682 |
252
+ | 0.2267 | 4.34 | 4000 | inf | 0.1654 |
253
+ | 0.2267 | 4.36 | 4020 | inf | 0.1724 |
254
+ | 0.2267 | 4.39 | 4040 | inf | 0.1777 |
255
+ | 0.2267 | 4.41 | 4060 | inf | 0.1721 |
256
+ | 0.2267 | 4.43 | 4080 | inf | 0.1770 |
257
+ | 0.2807 | 4.45 | 4100 | inf | 0.1717 |
258
+ | 0.2807 | 4.47 | 4120 | inf | 0.1773 |
259
+ | 0.2807 | 4.5 | 4140 | inf | 0.1777 |
260
+ | 0.2807 | 4.52 | 4160 | inf | 0.1657 |
261
+ | 0.2807 | 4.54 | 4180 | inf | 0.1692 |
262
+ | 0.2953 | 4.56 | 4200 | inf | 0.1699 |
263
+ | 0.2953 | 4.58 | 4220 | inf | 0.1650 |
264
+ | 0.2953 | 4.6 | 4240 | inf | 0.1731 |
265
+ | 0.2953 | 4.63 | 4260 | inf | 0.1685 |
266
+ | 0.2953 | 4.65 | 4280 | inf | 0.1721 |
267
+ | 0.2463 | 4.67 | 4300 | inf | 0.1643 |
268
+ | 0.2463 | 4.69 | 4320 | inf | 0.1636 |
269
+ | 0.2463 | 4.71 | 4340 | inf | 0.1657 |
270
+ | 0.2463 | 4.73 | 4360 | inf | 0.1678 |
271
+ | 0.2463 | 4.76 | 4380 | inf | 0.1759 |
272
+ | 0.313 | 4.78 | 4400 | inf | 0.1682 |
273
+ | 0.313 | 4.8 | 4420 | inf | 0.1671 |
274
+ | 0.313 | 4.82 | 4440 | inf | 0.1713 |
275
+ | 0.313 | 4.84 | 4460 | inf | 0.1675 |
276
+ | 0.313 | 4.86 | 4480 | inf | 0.1808 |
277
+ | 0.2748 | 4.89 | 4500 | inf | 0.1713 |
278
+ | 0.2748 | 4.91 | 4520 | inf | 0.1812 |
279
+ | 0.2748 | 4.93 | 4540 | inf | 0.1731 |
280
+ | 0.2748 | 4.95 | 4560 | inf | 0.1738 |
281
+ | 0.2748 | 4.97 | 4580 | inf | 0.1728 |
282
+ | 0.279 | 4.99 | 4600 | inf | 0.1745 |
283
+
284
+
285
+ ### Framework versions
286
+
287
+ - Transformers 4.32.0.dev0
288
+ - Pytorch 2.0.1+cu117
289
+ - Datasets 2.13.0
290
+ - Tokenizers 0.13.3