Hugging Face's logo

danieleV9H
/
wavlm-base-plus-ft-cv3

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
English
wavlm
generated_from_trainer
hf-asr-leaderboard
Eval Results
Inference Endpoints
Model card Files Metrics Community
danieleV9H commited on
Commit
d9a28c2
•
1 Parent(s): 871efe2

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +274 -0
README.md ADDED
@@ -0,0 +1,274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - common_voice
6
+ model-index:
7
+ - name: wavlm-base-plus-ft-cv3
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # wavlm-base-plus-ft-cv3
15
+
16
+ This model is a fine-tuned version of [microsoft/wavlm-base-plus](https://huggingface.co/microsoft/wavlm-base-plus) on the common_voice dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.4365
19
+ - Wer: 0.1801
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 11
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
50
+ |:-------------:|:-----:|:------:|:---------------:|:------:|
51
+ | 5.3448 | 0.05 | 500 | 3.2621 | 1.0 |
52
+ | 2.9322 | 0.1 | 1000 | 2.8551 | 1.0 |
53
+ | 1.7692 | 0.16 | 1500 | 1.2653 | 0.7447 |
54
+ | 1.012 | 0.21 | 2000 | 0.9008 | 0.5601 |
55
+ | 0.7129 | 0.26 | 2500 | 0.7684 | 0.4762 |
56
+ | 0.6424 | 0.31 | 3000 | 0.6282 | 0.4276 |
57
+ | 0.6518 | 0.37 | 3500 | 0.5888 | 0.3916 |
58
+ | 0.5142 | 0.42 | 4000 | 0.5428 | 0.3727 |
59
+ | 0.48 | 0.47 | 4500 | 0.5614 | 0.3549 |
60
+ | 0.4523 | 0.52 | 5000 | 0.5334 | 0.3487 |
61
+ | 0.4315 | 0.58 | 5500 | 0.5376 | 0.3317 |
62
+ | 0.4292 | 0.63 | 6000 | 0.4939 | 0.3172 |
63
+ | 0.4229 | 0.68 | 6500 | 0.4977 | 0.3117 |
64
+ | 0.3837 | 0.73 | 7000 | 0.4899 | 0.3056 |
65
+ | 0.385 | 0.78 | 7500 | 0.4571 | 0.2864 |
66
+ | 0.4155 | 0.84 | 8000 | 0.4635 | 0.2866 |
67
+ | 0.3768 | 0.89 | 8500 | 0.4390 | 0.2843 |
68
+ | 0.3864 | 0.94 | 9000 | 0.4529 | 0.2764 |
69
+ | 0.387 | 0.99 | 9500 | 0.4870 | 0.2755 |
70
+ | 0.341 | 1.05 | 10000 | 0.4498 | 0.2696 |
71
+ | 0.3334 | 1.1 | 10500 | 0.4355 | 0.2600 |
72
+ | 0.3039 | 1.15 | 11000 | 0.4634 | 0.2716 |
73
+ | 0.3101 | 1.2 | 11500 | 0.4615 | 0.2582 |
74
+ | 0.4343 | 1.25 | 12000 | 0.4510 | 0.2574 |
75
+ | 0.3002 | 1.31 | 12500 | 0.4313 | 0.2590 |
76
+ | 0.3419 | 1.36 | 13000 | 0.4121 | 0.2493 |
77
+ | 0.3162 | 1.41 | 13500 | 0.4423 | 0.2498 |
78
+ | 0.3134 | 1.46 | 14000 | 0.4260 | 0.2506 |
79
+ | 0.2963 | 1.52 | 14500 | 0.4272 | 0.2556 |
80
+ | 0.3297 | 1.57 | 15000 | 0.4413 | 0.2487 |
81
+ | 0.3199 | 1.62 | 15500 | 0.4260 | 0.2432 |
82
+ | 0.3368 | 1.67 | 16000 | 0.4164 | 0.2464 |
83
+ | 0.2981 | 1.73 | 16500 | 0.4111 | 0.2402 |
84
+ | 0.2887 | 1.78 | 17000 | 0.4372 | 0.2460 |
85
+ | 0.3058 | 1.83 | 17500 | 0.4161 | 0.2397 |
86
+ | 0.2877 | 1.88 | 18000 | 0.4046 | 0.2386 |
87
+ | 0.2904 | 1.93 | 18500 | 0.4108 | 0.2399 |
88
+ | 0.2851 | 1.99 | 19000 | 0.4196 | 0.2385 |
89
+ | 0.2451 | 2.04 | 19500 | 0.4096 | 0.2406 |
90
+ | 0.259 | 2.09 | 20000 | 0.4437 | 0.2374 |
91
+ | 0.2681 | 2.14 | 20500 | 0.4226 | 0.2357 |
92
+ | 0.4371 | 2.2 | 21000 | 0.4301 | 0.2356 |
93
+ | 0.2468 | 2.25 | 21500 | 0.4431 | 0.2326 |
94
+ | 0.2687 | 2.3 | 22000 | 0.4218 | 0.2401 |
95
+ | 0.2571 | 2.35 | 22500 | 0.4131 | 0.2337 |
96
+ | 0.2541 | 2.41 | 23000 | 0.4105 | 0.2312 |
97
+ | 0.2663 | 2.46 | 23500 | 0.4228 | 0.2327 |
98
+ | 0.2777 | 2.51 | 24000 | 0.3960 | 0.2254 |
99
+ | 0.2659 | 2.56 | 24500 | 0.4074 | 0.2289 |
100
+ | 0.2519 | 2.61 | 25000 | 0.4220 | 0.2363 |
101
+ | 0.2607 | 2.67 | 25500 | 0.3912 | 0.2253 |
102
+ | 0.2749 | 2.72 | 26000 | 0.4017 | 0.2214 |
103
+ | 0.2431 | 2.77 | 26500 | 0.3879 | 0.2181 |
104
+ | 0.2557 | 2.82 | 27000 | 0.4011 | 0.2268 |
105
+ | 0.2662 | 2.88 | 27500 | 0.3884 | 0.2241 |
106
+ | 0.2649 | 2.93 | 28000 | 0.3987 | 0.2233 |
107
+ | 0.2382 | 2.98 | 28500 | 0.3777 | 0.2215 |
108
+ | 0.2198 | 3.03 | 29000 | 0.3952 | 0.2177 |
109
+ | 0.2281 | 3.09 | 29500 | 0.4067 | 0.2213 |
110
+ | 0.2178 | 3.14 | 30000 | 0.4178 | 0.2192 |
111
+ | 0.222 | 3.19 | 30500 | 0.4327 | 0.2208 |
112
+ | 0.2262 | 3.24 | 31000 | 0.4028 | 0.2212 |
113
+ | 0.2256 | 3.29 | 31500 | 0.4065 | 0.2181 |
114
+ | 0.2255 | 3.35 | 32000 | 0.3782 | 0.2139 |
115
+ | 0.2364 | 3.4 | 32500 | 0.4443 | 0.2119 |
116
+ | 0.2209 | 3.45 | 33000 | 0.4089 | 0.2177 |
117
+ | 0.2051 | 3.5 | 33500 | 0.3886 | 0.2154 |
118
+ | 0.2242 | 3.56 | 34000 | 0.3810 | 0.2133 |
119
+ | 0.2151 | 3.61 | 34500 | 0.4005 | 0.2127 |
120
+ | 0.2341 | 3.66 | 35000 | 0.3899 | 0.2165 |
121
+ | 0.202 | 3.71 | 35500 | 0.3846 | 0.2121 |
122
+ | 0.2107 | 3.76 | 36000 | 0.3859 | 0.2146 |
123
+ | 0.2237 | 3.82 | 36500 | 0.3993 | 0.2141 |
124
+ | 0.2189 | 3.87 | 37000 | 0.3842 | 0.2113 |
125
+ | 0.2124 | 3.92 | 37500 | 0.3919 | 0.2118 |
126
+ | 0.4017 | 3.97 | 38000 | 0.3882 | 0.2086 |
127
+ | 0.1946 | 4.03 | 38500 | 0.4008 | 0.2121 |
128
+ | 0.1919 | 4.08 | 39000 | 0.3939 | 0.2129 |
129
+ | 0.1797 | 4.13 | 39500 | 0.3958 | 0.2115 |
130
+ | 0.184 | 4.18 | 40000 | 0.3942 | 0.2086 |
131
+ | 0.1987 | 4.24 | 40500 | 0.3959 | 0.2092 |
132
+ | 0.1919 | 4.29 | 41000 | 0.4250 | 0.2093 |
133
+ | 0.2038 | 4.34 | 41500 | 0.3970 | 0.2060 |
134
+ | 0.1879 | 4.39 | 42000 | 0.3978 | 0.2109 |
135
+ | 0.1852 | 4.44 | 42500 | 0.4065 | 0.2091 |
136
+ | 0.2014 | 4.5 | 43000 | 0.4069 | 0.2054 |
137
+ | 0.2011 | 4.55 | 43500 | 0.4247 | 0.2099 |
138
+ | 0.1937 | 4.6 | 44000 | 0.3754 | 0.2091 |
139
+ | 0.1878 | 4.65 | 44500 | 0.3891 | 0.2070 |
140
+ | 0.2011 | 4.71 | 45000 | 0.3714 | 0.2030 |
141
+ | 0.1958 | 4.76 | 45500 | 0.3994 | 0.2066 |
142
+ | 0.1907 | 4.81 | 46000 | 0.4061 | 0.2080 |
143
+ | 0.1859 | 4.86 | 46500 | 0.3899 | 0.2056 |
144
+ | 0.1894 | 4.92 | 47000 | 0.3808 | 0.2055 |
145
+ | 0.3276 | 4.97 | 47500 | 0.3936 | 0.2051 |
146
+ | 0.3513 | 5.02 | 48000 | 0.4028 | 0.2041 |
147
+ | 0.1654 | 5.07 | 48500 | 0.3929 | 0.2032 |
148
+ | 0.1622 | 5.12 | 49000 | 0.4067 | 0.2029 |
149
+ | 0.1659 | 5.18 | 49500 | 0.4058 | 0.2007 |
150
+ | 0.1779 | 5.23 | 50000 | 0.4085 | 0.2031 |
151
+ | 0.1731 | 5.28 | 50500 | 0.3895 | 0.2009 |
152
+ | 0.1761 | 5.33 | 51000 | 0.3973 | 0.2022 |
153
+ | 0.1741 | 5.39 | 51500 | 0.4116 | 0.2021 |
154
+ | 0.1735 | 5.44 | 52000 | 0.4152 | 0.2038 |
155
+ | 0.1627 | 5.49 | 52500 | 0.4078 | 0.2003 |
156
+ | 0.1728 | 5.54 | 53000 | 0.4088 | 0.2022 |
157
+ | 0.179 | 5.6 | 53500 | 0.3828 | 0.1998 |
158
+ | 0.1692 | 5.65 | 54000 | 0.3903 | 0.1980 |
159
+ | 0.174 | 5.7 | 54500 | 0.4185 | 0.1993 |
160
+ | 0.1763 | 5.75 | 55000 | 0.3937 | 0.1976 |
161
+ | 0.1792 | 5.8 | 55500 | 0.3767 | 0.1966 |
162
+ | 0.1799 | 5.86 | 56000 | 0.3970 | 0.1994 |
163
+ | 0.1918 | 5.91 | 56500 | 0.3954 | 0.1981 |
164
+ | 0.1836 | 5.96 | 57000 | 0.3984 | 0.1969 |
165
+ | 0.1708 | 6.01 | 57500 | 0.3917 | 0.1956 |
166
+ | 0.1524 | 6.07 | 58000 | 0.3922 | 0.1977 |
167
+ | 0.1567 | 6.12 | 58500 | 0.4108 | 0.1955 |
168
+ | 0.1518 | 6.17 | 59000 | 0.4349 | 0.1968 |
169
+ | 0.1587 | 6.22 | 59500 | 0.3963 | 0.1988 |
170
+ | 0.1563 | 6.27 | 60000 | 0.4235 | 0.1997 |
171
+ | 0.154 | 6.33 | 60500 | 0.4026 | 0.1951 |
172
+ | 0.1636 | 6.38 | 61000 | 0.4359 | 0.2031 |
173
+ | 0.1641 | 6.43 | 61500 | 0.4115 | 0.1972 |
174
+ | 0.1604 | 6.48 | 62000 | 0.4166 | 0.1972 |
175
+ | 0.1579 | 6.54 | 62500 | 0.4264 | 0.1965 |
176
+ | 0.1552 | 6.59 | 63000 | 0.4047 | 0.2007 |
177
+ | 0.1461 | 6.64 | 63500 | 0.4263 | 0.2011 |
178
+ | 0.1522 | 6.69 | 64000 | 0.4222 | 0.1970 |
179
+ | 0.1624 | 6.75 | 64500 | 0.4318 | 0.1971 |
180
+ | 0.1474 | 6.8 | 65000 | 0.4265 | 0.1961 |
181
+ | 0.1495 | 6.85 | 65500 | 0.4316 | 0.1940 |
182
+ | 0.1509 | 6.9 | 66000 | 0.4297 | 0.1965 |
183
+ | 0.1479 | 6.95 | 66500 | 0.4232 | 0.1966 |
184
+ | 0.1462 | 7.01 | 67000 | 0.4090 | 0.1946 |
185
+ | 0.1498 | 7.06 | 67500 | 0.4197 | 0.1939 |
186
+ | 0.1436 | 7.11 | 68000 | 0.4215 | 0.1956 |
187
+ | 0.1378 | 7.16 | 68500 | 0.4345 | 0.1968 |
188
+ | 0.3082 | 7.22 | 69000 | 0.4364 | 0.1972 |
189
+ | 0.1386 | 7.27 | 69500 | 0.4284 | 0.1949 |
190
+ | 0.1441 | 7.32 | 70000 | 0.4019 | 0.1953 |
191
+ | 0.1624 | 7.37 | 70500 | 0.4175 | 0.1951 |
192
+ | 0.1454 | 7.43 | 71000 | 0.4224 | 0.1922 |
193
+ | 0.1408 | 7.48 | 71500 | 0.4128 | 0.1961 |
194
+ | 0.1525 | 7.53 | 72000 | 0.4200 | 0.1946 |
195
+ | 0.1459 | 7.58 | 72500 | 0.4166 | 0.1949 |
196
+ | 0.1485 | 7.63 | 73000 | 0.4102 | 0.1947 |
197
+ | 0.148 | 7.69 | 73500 | 0.4237 | 0.1948 |
198
+ | 0.1478 | 7.74 | 74000 | 0.4104 | 0.1928 |
199
+ | 0.14 | 7.79 | 74500 | 0.4027 | 0.1928 |
200
+ | 0.1473 | 7.84 | 75000 | 0.4034 | 0.1907 |
201
+ | 0.1394 | 7.9 | 75500 | 0.3823 | 0.1923 |
202
+ | 0.1324 | 7.95 | 76000 | 0.3987 | 0.1899 |
203
+ | 0.1459 | 8.0 | 76500 | 0.4003 | 0.1907 |
204
+ | 0.1373 | 8.05 | 77000 | 0.4204 | 0.1925 |
205
+ | 0.1303 | 8.1 | 77500 | 0.4218 | 0.1907 |
206
+ | 0.1346 | 8.16 | 78000 | 0.4091 | 0.1882 |
207
+ | 0.2947 | 8.21 | 78500 | 0.4156 | 0.1890 |
208
+ | 0.1324 | 8.26 | 79000 | 0.4280 | 0.1888 |
209
+ | 0.132 | 8.31 | 79500 | 0.4136 | 0.1873 |
210
+ | 0.1377 | 8.37 | 80000 | 0.4099 | 0.1915 |
211
+ | 0.3045 | 8.42 | 80500 | 0.4201 | 0.1900 |
212
+ | 0.1372 | 8.47 | 81000 | 0.4161 | 0.1876 |
213
+ | 0.1377 | 8.52 | 81500 | 0.4107 | 0.1869 |
214
+ | 0.1374 | 8.58 | 82000 | 0.4188 | 0.1875 |
215
+ | 0.1301 | 8.63 | 82500 | 0.4306 | 0.1860 |
216
+ | 0.1386 | 8.68 | 83000 | 0.4131 | 0.1862 |
217
+ | 0.1292 | 8.73 | 83500 | 0.3997 | 0.1871 |
218
+ | 0.1276 | 8.78 | 84000 | 0.4237 | 0.1873 |
219
+ | 0.1377 | 8.84 | 84500 | 0.4284 | 0.1889 |
220
+ | 0.1338 | 8.89 | 85000 | 0.4205 | 0.1861 |
221
+ | 0.1284 | 8.94 | 85500 | 0.4380 | 0.1875 |
222
+ | 0.1471 | 8.99 | 86000 | 0.4238 | 0.1895 |
223
+ | 0.1186 | 9.05 | 86500 | 0.4128 | 0.1875 |
224
+ | 0.1222 | 9.1 | 87000 | 0.4267 | 0.1864 |
225
+ | 0.1229 | 9.15 | 87500 | 0.4169 | 0.1842 |
226
+ | 0.1259 | 9.2 | 88000 | 0.4327 | 0.1861 |
227
+ | 0.1281 | 9.26 | 88500 | 0.4188 | 0.1877 |
228
+ | 0.1247 | 9.31 | 89000 | 0.4212 | 0.1852 |
229
+ | 0.1248 | 9.36 | 89500 | 0.4172 | 0.1863 |
230
+ | 0.1232 | 9.41 | 90000 | 0.4173 | 0.1858 |
231
+ | 0.3255 | 9.46 | 90500 | 0.4225 | 0.1851 |
232
+ | 0.1243 | 9.52 | 91000 | 0.4290 | 0.1849 |
233
+ | 0.1266 | 9.57 | 91500 | 0.4186 | 0.1842 |
234
+ | 0.1257 | 9.62 | 92000 | 0.4364 | 0.1860 |
235
+ | 0.1181 | 9.67 | 92500 | 0.4294 | 0.1852 |
236
+ | 0.1202 | 9.73 | 93000 | 0.4222 | 0.1836 |
237
+ | 0.1264 | 9.78 | 93500 | 0.4191 | 0.1856 |
238
+ | 0.1243 | 9.83 | 94000 | 0.4237 | 0.1856 |
239
+ | 0.1164 | 9.88 | 94500 | 0.4281 | 0.1848 |
240
+ | 0.1283 | 9.94 | 95000 | 0.4332 | 0.1845 |
241
+ | 0.123 | 9.99 | 95500 | 0.4316 | 0.1839 |
242
+ | 0.1232 | 10.04 | 96000 | 0.4313 | 0.1844 |
243
+ | 0.1206 | 10.09 | 96500 | 0.4303 | 0.1840 |
244
+ | 0.1145 | 10.14 | 97000 | 0.4299 | 0.1822 |
245
+ | 0.1265 | 10.2 | 97500 | 0.4266 | 0.1822 |
246
+ | 0.1147 | 10.25 | 98000 | 0.4322 | 0.1844 |
247
+ | 0.1122 | 10.3 | 98500 | 0.4251 | 0.1830 |
248
+ | 0.1101 | 10.35 | 99000 | 0.4297 | 0.1830 |
249
+ | 0.1225 | 10.41 | 99500 | 0.4244 | 0.1842 |
250
+ | 0.1177 | 10.46 | 100000 | 0.4343 | 0.1826 |
251
+ | 0.1157 | 10.51 | 100500 | 0.4228 | 0.1827 |
252
+ | 0.1215 | 10.56 | 101000 | 0.4285 | 0.1814 |
253
+ | 0.276 | 10.61 | 101500 | 0.4268 | 0.1820 |
254
+ | 0.111 | 10.67 | 102000 | 0.4288 | 0.1836 |
255
+ | 0.1164 | 10.72 | 102500 | 0.4283 | 0.1825 |
256
+ | 0.111 | 10.77 | 103000 | 0.4198 | 0.1819 |
257
+ | 0.1135 | 10.82 | 103500 | 0.4333 | 0.1818 |
258
+ | 0.1196 | 10.88 | 104000 | 0.4239 | 0.1817 |
259
+ | 0.1176 | 10.93 | 104500 | 0.4252 | 0.1819 |
260
+ | 0.117 | 10.98 | 105000 | 0.4317 | 0.1820 |
261
+ | 0.1166 | 11.03 | 105500 | 0.4307 | 0.1815 |
262
+ | 0.1118 | 11.09 | 106000 | 0.4379 | 0.1821 |
263
+ | 0.1116 | 11.14 | 106500 | 0.4363 | 0.1812 |
264
+ | 0.1098 | 11.19 | 107000 | 0.4328 | 0.1816 |
265
+ | 0.1134 | 11.24 | 107500 | 0.4284 | 0.1811 |
266
+ | 0.1104 | 11.29 | 108000 | 0.4365 | 0.1801 |
267
+
268
+
269
+ ### Framework versions
270
+
271
+ - Transformers 4.19.2
272
+ - Pytorch 1.11.0+cu113
273
+ - Datasets 2.2.0
274
+ - Tokenizers 0.12.1