Hugging Face's logo

dbdmg
/
wav2vec2-xls-r-1b-italian-robust

Automatic Speech Recognition
Transformers
PyTorch
Safetensors
Italian
wav2vec2
Generated from Trainer
hf-asr-leaderboard
robust-speech-event
Eval Results
Inference Endpoints
Model card Files Community
1
Moreno La Quatra commited on
Commit
0228215
•
1 Parent(s): 1031498

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +206 -0
README.md ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: wav2vec2-xls-r-1b-italian-augmented-cv-ls
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # wav2vec2-xls-r-1b-italian-augmented-cv-ls
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.2428
18
+ - Wer: 0.2960
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 500
44
+ - num_epochs: 10.0
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
50
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
51
+ | No log | 0.07 | 400 | 1.0053 | 0.8058 |
52
+ | 1.5087 | 0.13 | 800 | 0.9127 | 0.8104 |
53
+ | 0.9552 | 0.2 | 1200 | 1.0360 | 0.8836 |
54
+ | 0.9555 | 0.27 | 1600 | 0.9980 | 0.8577 |
55
+ | 1.0259 | 0.34 | 2000 | 1.0103 | 0.8842 |
56
+ | 1.0259 | 0.4 | 2400 | 0.9119 | 0.8466 |
57
+ | 1.0365 | 0.47 | 2800 | 0.9000 | 0.8281 |
58
+ | 1.0069 | 0.54 | 3200 | 0.7976 | 0.7875 |
59
+ | 0.9688 | 0.61 | 3600 | 0.8126 | 0.8051 |
60
+ | 0.9638 | 0.67 | 4000 | 0.7921 | 0.7903 |
61
+ | 0.9638 | 0.74 | 4400 | 0.7703 | 0.7783 |
62
+ | 0.9327 | 0.81 | 4800 | 0.7253 | 0.7463 |
63
+ | 0.8992 | 0.88 | 5200 | 0.6841 | 0.7171 |
64
+ | 0.8693 | 0.94 | 5600 | 0.6867 | 0.7250 |
65
+ | 0.8433 | 1.01 | 6000 | 0.7077 | 0.7302 |
66
+ | 0.8433 | 1.08 | 6400 | 0.6685 | 0.7091 |
67
+ | 0.8499 | 1.14 | 6800 | 0.6355 | 0.6825 |
68
+ | 0.8159 | 1.21 | 7200 | 0.6283 | 0.6800 |
69
+ | 0.8001 | 1.28 | 7600 | 0.6288 | 0.6743 |
70
+ | 0.7883 | 1.35 | 8000 | 0.5995 | 0.6633 |
71
+ | 0.7883 | 1.41 | 8400 | 0.6195 | 0.6726 |
72
+ | 0.7863 | 1.48 | 8800 | 0.6039 | 0.6588 |
73
+ | 0.7713 | 1.55 | 9200 | 0.5842 | 0.6490 |
74
+ | 0.7572 | 1.62 | 9600 | 0.5975 | 0.6533 |
75
+ | 0.7442 | 1.68 | 10000 | 0.5508 | 0.6233 |
76
+ | 0.7442 | 1.75 | 10400 | 0.5521 | 0.6209 |
77
+ | 0.7296 | 1.82 | 10800 | 0.5760 | 0.6245 |
78
+ | 0.7205 | 1.89 | 11200 | 0.5593 | 0.6144 |
79
+ | 0.7106 | 1.95 | 11600 | 0.5672 | 0.6220 |
80
+ | 0.7146 | 2.02 | 12000 | 0.5134 | 0.5911 |
81
+ | 0.7146 | 2.09 | 12400 | 0.5069 | 0.5811 |
82
+ | 0.6944 | 2.15 | 12800 | 0.5022 | 0.5962 |
83
+ | 0.6817 | 2.22 | 13200 | 0.4989 | 0.5813 |
84
+ | 0.6721 | 2.29 | 13600 | 0.4941 | 0.5742 |
85
+ | 0.6774 | 2.36 | 14000 | 0.4775 | 0.5676 |
86
+ | 0.6774 | 2.42 | 14400 | 0.4694 | 0.5525 |
87
+ | 0.6621 | 2.49 | 14800 | 0.4720 | 0.5514 |
88
+ | 0.6599 | 2.56 | 15200 | 0.4714 | 0.5553 |
89
+ | 0.6591 | 2.63 | 15600 | 0.4578 | 0.5397 |
90
+ | 0.645 | 2.69 | 16000 | 0.4619 | 0.5452 |
91
+ | 0.645 | 2.76 | 16400 | 0.4578 | 0.5343 |
92
+ | 0.6431 | 2.83 | 16800 | 0.4514 | 0.5328 |
93
+ | 0.636 | 2.9 | 17200 | 0.4526 | 0.5325 |
94
+ | 0.6433 | 2.96 | 17600 | 0.4561 | 0.5325 |
95
+ | 0.6356 | 3.03 | 18000 | 0.4386 | 0.5191 |
96
+ | 0.6356 | 3.1 | 18400 | 0.4291 | 0.5065 |
97
+ | 0.6175 | 3.16 | 18800 | 0.4306 | 0.5170 |
98
+ | 0.6187 | 3.23 | 19200 | 0.4256 | 0.5036 |
99
+ | 0.607 | 3.3 | 19600 | 0.4198 | 0.5027 |
100
+ | 0.6004 | 3.37 | 20000 | 0.4149 | 0.4906 |
101
+ | 0.6004 | 3.43 | 20400 | 0.4114 | 0.4902 |
102
+ | 0.6002 | 3.5 | 20800 | 0.4116 | 0.4967 |
103
+ | 0.5926 | 3.57 | 21200 | 0.4066 | 0.4843 |
104
+ | 0.5836 | 3.64 | 21600 | 0.3956 | 0.4791 |
105
+ | 0.588 | 3.7 | 22000 | 0.3941 | 0.4729 |
106
+ | 0.588 | 3.77 | 22400 | 0.3972 | 0.4799 |
107
+ | 0.5739 | 3.84 | 22800 | 0.4018 | 0.4790 |
108
+ | 0.5778 | 3.91 | 23200 | 0.3936 | 0.4750 |
109
+ | 0.5768 | 3.97 | 23600 | 0.3936 | 0.4751 |
110
+ | 0.5651 | 4.04 | 24000 | 0.3953 | 0.4706 |
111
+ | 0.5651 | 4.11 | 24400 | 0.3906 | 0.4659 |
112
+ | 0.5704 | 4.17 | 24800 | 0.3807 | 0.4557 |
113
+ | 0.5594 | 4.24 | 25200 | 0.3817 | 0.4610 |
114
+ | 0.5509 | 4.31 | 25600 | 0.3755 | 0.4553 |
115
+ | 0.5439 | 4.38 | 26000 | 0.3705 | 0.4471 |
116
+ | 0.5439 | 4.44 | 26400 | 0.3744 | 0.4487 |
117
+ | 0.5426 | 4.51 | 26800 | 0.3716 | 0.4483 |
118
+ | 0.5393 | 4.58 | 27200 | 0.3600 | 0.4356 |
119
+ | 0.5408 | 4.65 | 27600 | 0.3573 | 0.4307 |
120
+ | 0.5327 | 4.71 | 28000 | 0.3638 | 0.4382 |
121
+ | 0.5327 | 4.78 | 28400 | 0.3587 | 0.4316 |
122
+ | 0.5324 | 4.85 | 28800 | 0.3598 | 0.4290 |
123
+ | 0.5378 | 4.91 | 29200 | 0.3508 | 0.4243 |
124
+ | 0.5246 | 4.98 | 29600 | 0.3522 | 0.4260 |
125
+ | 0.5284 | 5.05 | 30000 | 0.3520 | 0.4268 |
126
+ | 0.5284 | 5.12 | 30400 | 0.3506 | 0.4224 |
127
+ | 0.5154 | 5.18 | 30800 | 0.3556 | 0.4223 |
128
+ | 0.5138 | 5.25 | 31200 | 0.3526 | 0.4276 |
129
+ | 0.51 | 5.32 | 31600 | 0.3440 | 0.4220 |
130
+ | 0.5065 | 5.39 | 32000 | 0.3367 | 0.4120 |
131
+ | 0.5065 | 5.45 | 32400 | 0.3406 | 0.4136 |
132
+ | 0.5087 | 5.52 | 32800 | 0.3370 | 0.4125 |
133
+ | 0.503 | 5.59 | 33200 | 0.3387 | 0.4134 |
134
+ | 0.5085 | 5.66 | 33600 | 0.3346 | 0.4068 |
135
+ | 0.5044 | 5.72 | 34000 | 0.3325 | 0.4057 |
136
+ | 0.5044 | 5.79 | 34400 | 0.3304 | 0.4026 |
137
+ | 0.4879 | 5.86 | 34800 | 0.3274 | 0.4002 |
138
+ | 0.4924 | 5.92 | 35200 | 0.3286 | 0.3980 |
139
+ | 0.4991 | 5.99 | 35600 | 0.3231 | 0.3952 |
140
+ | 0.487 | 6.06 | 36000 | 0.3324 | 0.4005 |
141
+ | 0.487 | 6.13 | 36400 | 0.3264 | 0.3952 |
142
+ | 0.4754 | 6.19 | 36800 | 0.3234 | 0.3905 |
143
+ | 0.4683 | 6.26 | 37200 | 0.3149 | 0.3840 |
144
+ | 0.4653 | 6.33 | 37600 | 0.3122 | 0.3824 |
145
+ | 0.4667 | 6.4 | 38000 | 0.3151 | 0.3855 |
146
+ | 0.4667 | 6.46 | 38400 | 0.3217 | 0.3859 |
147
+ | 0.4628 | 6.53 | 38800 | 0.3085 | 0.3831 |
148
+ | 0.4644 | 6.6 | 39200 | 0.3121 | 0.3791 |
149
+ | 0.4612 | 6.67 | 39600 | 0.3093 | 0.3790 |
150
+ | 0.4552 | 6.73 | 40000 | 0.3087 | 0.3749 |
151
+ | 0.4552 | 6.8 | 40400 | 0.3027 | 0.3679 |
152
+ | 0.4544 | 6.87 | 40800 | 0.3048 | 0.3672 |
153
+ | 0.4507 | 6.93 | 41200 | 0.2963 | 0.3614 |
154
+ | 0.4489 | 7.0 | 41600 | 0.3086 | 0.3718 |
155
+ | 0.4367 | 7.07 | 42000 | 0.3100 | 0.3754 |
156
+ | 0.4367 | 7.14 | 42400 | 0.3057 | 0.3701 |
157
+ | 0.4376 | 7.2 | 42800 | 0.2930 | 0.3614 |
158
+ | 0.428 | 7.27 | 43200 | 0.2907 | 0.3516 |
159
+ | 0.4241 | 7.34 | 43600 | 0.2916 | 0.3590 |
160
+ | 0.4312 | 7.41 | 44000 | 0.2904 | 0.3523 |
161
+ | 0.4312 | 7.47 | 44400 | 0.2908 | 0.3476 |
162
+ | 0.4292 | 7.54 | 44800 | 0.2858 | 0.3467 |
163
+ | 0.426 | 7.61 | 45200 | 0.2864 | 0.3484 |
164
+ | 0.4225 | 7.68 | 45600 | 0.2820 | 0.3441 |
165
+ | 0.422 | 7.74 | 46000 | 0.2834 | 0.3441 |
166
+ | 0.422 | 7.81 | 46400 | 0.2784 | 0.3420 |
167
+ | 0.4158 | 7.88 | 46800 | 0.2814 | 0.3390 |
168
+ | 0.4139 | 7.94 | 47200 | 0.2777 | 0.3384 |
169
+ | 0.4076 | 8.01 | 47600 | 0.2741 | 0.3381 |
170
+ | 0.3997 | 8.08 | 48000 | 0.2738 | 0.3320 |
171
+ | 0.3997 | 8.15 | 48400 | 0.2720 | 0.3303 |
172
+ | 0.4009 | 8.21 | 48800 | 0.2705 | 0.3357 |
173
+ | 0.3928 | 8.28 | 49200 | 0.2708 | 0.3265 |
174
+ | 0.3923 | 8.35 | 49600 | 0.2678 | 0.3283 |
175
+ | 0.3897 | 8.42 | 50000 | 0.2649 | 0.3241 |
176
+ | 0.3897 | 8.48 | 50400 | 0.2640 | 0.3218 |
177
+ | 0.3879 | 8.55 | 50800 | 0.2616 | 0.3197 |
178
+ | 0.3805 | 8.62 | 51200 | 0.2599 | 0.3170 |
179
+ | 0.3874 | 8.69 | 51600 | 0.2592 | 0.3168 |
180
+ | 0.3799 | 8.75 | 52000 | 0.2589 | 0.3157 |
181
+ | 0.3799 | 8.82 | 52400 | 0.2566 | 0.3137 |
182
+ | 0.3834 | 8.89 | 52800 | 0.2552 | 0.3141 |
183
+ | 0.3811 | 8.95 | 53200 | 0.2523 | 0.3108 |
184
+ | 0.3821 | 9.02 | 53600 | 0.2539 | 0.3112 |
185
+ | 0.3636 | 9.09 | 54000 | 0.2529 | 0.3070 |
186
+ | 0.3636 | 9.16 | 54400 | 0.2500 | 0.3078 |
187
+ | 0.3706 | 9.22 | 54800 | 0.2510 | 0.3067 |
188
+ | 0.367 | 9.29 | 55200 | 0.2497 | 0.3069 |
189
+ | 0.3618 | 9.36 | 55600 | 0.2493 | 0.3043 |
190
+ | 0.3624 | 9.43 | 56000 | 0.2491 | 0.3040 |
191
+ | 0.3624 | 9.49 | 56400 | 0.2466 | 0.3016 |
192
+ | 0.3557 | 9.56 | 56800 | 0.2460 | 0.3014 |
193
+ | 0.3536 | 9.63 | 57200 | 0.2470 | 0.2997 |
194
+ | 0.3584 | 9.7 | 57600 | 0.2441 | 0.2989 |
195
+ | 0.3563 | 9.76 | 58000 | 0.2442 | 0.2970 |
196
+ | 0.3563 | 9.83 | 58400 | 0.2436 | 0.2966 |
197
+ | 0.3492 | 9.9 | 58800 | 0.2431 | 0.2967 |
198
+ | 0.3483 | 9.96 | 59200 | 0.2428 | 0.2960 |
199
+
200
+
201
+ ### Framework versions
202
+
203
+ - Transformers 4.17.0.dev0
204
+ - Pytorch 1.10.2+cu102
205
+ - Datasets 1.18.3
206
+ - Tokenizers 0.11.0