Commit
•
e86214c
1
Parent(s):
5eb2257
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,174 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- common_voice
|
6 |
+
model-index:
|
7 |
+
- name: wav2vec2-large-xls-r-300m-spanish-small
|
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 |
+
# wav2vec2-large-xls-r-300m-spanish-small
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [jhonparra18/wav2vec2-large-xls-r-300m-spanish-custom](https://huggingface.co/jhonparra18/wav2vec2-large-xls-r-300m-spanish-custom) on the common_voice dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.3763
|
19 |
+
- Wer: 0.1791
|
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: 0.0003
|
39 |
+
- train_batch_size: 8
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 2
|
43 |
+
- total_train_batch_size: 16
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_steps: 500
|
47 |
+
- num_epochs: 30
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
54 |
+
| 0.2277 | 0.26 | 400 | 0.2601 | 0.2291 |
|
55 |
+
| 0.2932 | 0.53 | 800 | 0.2950 | 0.2670 |
|
56 |
+
| 0.3019 | 0.79 | 1200 | 0.3247 | 0.2766 |
|
57 |
+
| 0.2987 | 1.05 | 1600 | 0.3031 | 0.2606 |
|
58 |
+
| 0.261 | 1.32 | 2000 | 0.2994 | 0.2620 |
|
59 |
+
| 0.2651 | 1.58 | 2400 | 0.3134 | 0.2700 |
|
60 |
+
| 0.264 | 1.85 | 2800 | 0.3016 | 0.2641 |
|
61 |
+
| 0.2475 | 2.11 | 3200 | 0.3135 | 0.2661 |
|
62 |
+
| 0.2269 | 2.37 | 3600 | 0.3029 | 0.2562 |
|
63 |
+
| 0.2389 | 2.64 | 4000 | 0.3035 | 0.2549 |
|
64 |
+
| 0.2319 | 2.9 | 4400 | 0.3022 | 0.2551 |
|
65 |
+
| 0.2123 | 3.16 | 4800 | 0.3256 | 0.2638 |
|
66 |
+
| 0.2094 | 3.43 | 5200 | 0.3227 | 0.2712 |
|
67 |
+
| 0.2121 | 3.69 | 5600 | 0.3085 | 0.2596 |
|
68 |
+
| 0.207 | 3.96 | 6000 | 0.3041 | 0.2597 |
|
69 |
+
| 0.1809 | 4.22 | 6400 | 0.3122 | 0.2524 |
|
70 |
+
| 0.1846 | 4.48 | 6800 | 0.3254 | 0.2579 |
|
71 |
+
| 0.1885 | 4.75 | 7200 | 0.2958 | 0.2437 |
|
72 |
+
| 0.1923 | 5.01 | 7600 | 0.3136 | 0.2502 |
|
73 |
+
| 0.1626 | 5.27 | 8000 | 0.3059 | 0.2488 |
|
74 |
+
| 0.1704 | 5.54 | 8400 | 0.3082 | 0.2515 |
|
75 |
+
| 0.1674 | 5.8 | 8800 | 0.3196 | 0.2509 |
|
76 |
+
| 0.1691 | 6.06 | 9200 | 0.3193 | 0.25 |
|
77 |
+
| 0.1499 | 6.33 | 9600 | 0.3529 | 0.2635 |
|
78 |
+
| 0.1568 | 6.59 | 10000 | 0.3241 | 0.2481 |
|
79 |
+
| 0.1538 | 6.86 | 10400 | 0.3354 | 0.2476 |
|
80 |
+
| 0.1503 | 7.12 | 10800 | 0.3180 | 0.2402 |
|
81 |
+
| 0.136 | 7.38 | 11200 | 0.3230 | 0.2397 |
|
82 |
+
| 0.1413 | 7.65 | 11600 | 0.3178 | 0.2451 |
|
83 |
+
| 0.147 | 7.91 | 12000 | 0.3170 | 0.2389 |
|
84 |
+
| 0.1341 | 8.17 | 12400 | 0.3380 | 0.2501 |
|
85 |
+
| 0.1329 | 8.44 | 12800 | 0.3265 | 0.2414 |
|
86 |
+
| 0.1314 | 8.7 | 13200 | 0.3281 | 0.2482 |
|
87 |
+
| 0.1312 | 8.97 | 13600 | 0.3259 | 0.2539 |
|
88 |
+
| 0.12 | 9.23 | 14000 | 0.3291 | 0.2424 |
|
89 |
+
| 0.1193 | 9.49 | 14400 | 0.3302 | 0.2412 |
|
90 |
+
| 0.1189 | 9.76 | 14800 | 0.3376 | 0.2407 |
|
91 |
+
| 0.1217 | 10.02 | 15200 | 0.3334 | 0.2400 |
|
92 |
+
| 0.1118 | 10.28 | 15600 | 0.3359 | 0.2368 |
|
93 |
+
| 0.1139 | 10.55 | 16000 | 0.3239 | 0.2335 |
|
94 |
+
| 0.1106 | 10.81 | 16400 | 0.3374 | 0.2352 |
|
95 |
+
| 0.1081 | 11.07 | 16800 | 0.3585 | 0.2434 |
|
96 |
+
| 0.1063 | 11.34 | 17200 | 0.3639 | 0.2472 |
|
97 |
+
| 0.1041 | 11.6 | 17600 | 0.3399 | 0.2423 |
|
98 |
+
| 0.1062 | 11.87 | 18000 | 0.3410 | 0.2388 |
|
99 |
+
| 0.1012 | 12.13 | 18400 | 0.3597 | 0.2413 |
|
100 |
+
| 0.0953 | 12.39 | 18800 | 0.3440 | 0.2296 |
|
101 |
+
| 0.097 | 12.66 | 19200 | 0.3440 | 0.2269 |
|
102 |
+
| 0.0968 | 12.92 | 19600 | 0.3498 | 0.2333 |
|
103 |
+
| 0.0902 | 13.18 | 20000 | 0.3471 | 0.2290 |
|
104 |
+
| 0.0868 | 13.45 | 20400 | 0.3462 | 0.2266 |
|
105 |
+
| 0.0892 | 13.71 | 20800 | 0.3373 | 0.2227 |
|
106 |
+
| 0.0902 | 13.97 | 21200 | 0.3377 | 0.2240 |
|
107 |
+
| 0.0846 | 14.24 | 21600 | 0.3484 | 0.2237 |
|
108 |
+
| 0.0839 | 14.5 | 22000 | 0.3706 | 0.2260 |
|
109 |
+
| 0.0834 | 14.77 | 22400 | 0.3430 | 0.2268 |
|
110 |
+
| 0.0841 | 15.03 | 22800 | 0.3489 | 0.2259 |
|
111 |
+
| 0.076 | 15.29 | 23200 | 0.3626 | 0.2281 |
|
112 |
+
| 0.0771 | 15.56 | 23600 | 0.3624 | 0.2268 |
|
113 |
+
| 0.0773 | 15.82 | 24000 | 0.3440 | 0.2252 |
|
114 |
+
| 0.0759 | 16.08 | 24400 | 0.3532 | 0.2170 |
|
115 |
+
| 0.0745 | 16.35 | 24800 | 0.3686 | 0.2188 |
|
116 |
+
| 0.0713 | 16.61 | 25200 | 0.3691 | 0.2195 |
|
117 |
+
| 0.0718 | 16.88 | 25600 | 0.3470 | 0.2108 |
|
118 |
+
| 0.0685 | 17.14 | 26000 | 0.3756 | 0.2179 |
|
119 |
+
| 0.0689 | 17.4 | 26400 | 0.3542 | 0.2149 |
|
120 |
+
| 0.0671 | 17.67 | 26800 | 0.3461 | 0.2165 |
|
121 |
+
| 0.0737 | 17.93 | 27200 | 0.3473 | 0.2238 |
|
122 |
+
| 0.0669 | 18.19 | 27600 | 0.3441 | 0.2138 |
|
123 |
+
| 0.0629 | 18.46 | 28000 | 0.3721 | 0.2155 |
|
124 |
+
| 0.0632 | 18.72 | 28400 | 0.3667 | 0.2126 |
|
125 |
+
| 0.0647 | 18.98 | 28800 | 0.3579 | 0.2097 |
|
126 |
+
| 0.0603 | 19.25 | 29200 | 0.3670 | 0.2130 |
|
127 |
+
| 0.0604 | 19.51 | 29600 | 0.3750 | 0.2142 |
|
128 |
+
| 0.0619 | 19.78 | 30000 | 0.3804 | 0.2160 |
|
129 |
+
| 0.0603 | 20.04 | 30400 | 0.3764 | 0.2124 |
|
130 |
+
| 0.0577 | 20.3 | 30800 | 0.3858 | 0.2097 |
|
131 |
+
| 0.0583 | 20.57 | 31200 | 0.3520 | 0.2089 |
|
132 |
+
| 0.0561 | 20.83 | 31600 | 0.3615 | 0.2079 |
|
133 |
+
| 0.0545 | 21.09 | 32000 | 0.3824 | 0.2032 |
|
134 |
+
| 0.0525 | 21.36 | 32400 | 0.3858 | 0.2091 |
|
135 |
+
| 0.0524 | 21.62 | 32800 | 0.3956 | 0.2099 |
|
136 |
+
| 0.0527 | 21.89 | 33200 | 0.3667 | 0.2025 |
|
137 |
+
| 0.0514 | 22.15 | 33600 | 0.3708 | 0.2032 |
|
138 |
+
| 0.0506 | 22.41 | 34000 | 0.3815 | 0.2053 |
|
139 |
+
| 0.0478 | 22.68 | 34400 | 0.3671 | 0.2007 |
|
140 |
+
| 0.049 | 22.94 | 34800 | 0.3758 | 0.2003 |
|
141 |
+
| 0.0477 | 23.2 | 35200 | 0.3786 | 0.2014 |
|
142 |
+
| 0.045 | 23.47 | 35600 | 0.3732 | 0.1998 |
|
143 |
+
| 0.0426 | 23.73 | 36000 | 0.3737 | 0.2010 |
|
144 |
+
| 0.0444 | 23.99 | 36400 | 0.3600 | 0.1990 |
|
145 |
+
| 0.0433 | 24.26 | 36800 | 0.3689 | 0.1976 |
|
146 |
+
| 0.0442 | 24.52 | 37200 | 0.3787 | 0.1968 |
|
147 |
+
| 0.0419 | 24.79 | 37600 | 0.3652 | 0.1961 |
|
148 |
+
| 0.042 | 25.05 | 38000 | 0.3820 | 0.1964 |
|
149 |
+
| 0.0419 | 25.31 | 38400 | 0.3786 | 0.1919 |
|
150 |
+
| 0.0376 | 25.58 | 38800 | 0.3842 | 0.1934 |
|
151 |
+
| 0.0385 | 25.84 | 39200 | 0.3767 | 0.1900 |
|
152 |
+
| 0.0396 | 26.1 | 39600 | 0.3688 | 0.1888 |
|
153 |
+
| 0.0371 | 26.37 | 40000 | 0.3815 | 0.1894 |
|
154 |
+
| 0.0363 | 26.63 | 40400 | 0.3748 | 0.1878 |
|
155 |
+
| 0.0377 | 26.9 | 40800 | 0.3713 | 0.1852 |
|
156 |
+
| 0.0352 | 27.16 | 41200 | 0.3734 | 0.1851 |
|
157 |
+
| 0.0355 | 27.42 | 41600 | 0.3776 | 0.1874 |
|
158 |
+
| 0.0333 | 27.69 | 42000 | 0.3867 | 0.1841 |
|
159 |
+
| 0.0348 | 27.95 | 42400 | 0.3823 | 0.1839 |
|
160 |
+
| 0.0329 | 28.21 | 42800 | 0.3795 | 0.1822 |
|
161 |
+
| 0.0325 | 28.48 | 43200 | 0.3711 | 0.1813 |
|
162 |
+
| 0.0328 | 28.74 | 43600 | 0.3721 | 0.1781 |
|
163 |
+
| 0.0312 | 29.0 | 44000 | 0.3803 | 0.1816 |
|
164 |
+
| 0.0318 | 29.27 | 44400 | 0.3758 | 0.1794 |
|
165 |
+
| 0.0302 | 29.53 | 44800 | 0.3792 | 0.1784 |
|
166 |
+
| 0.0339 | 29.8 | 45200 | 0.3763 | 0.1791 |
|
167 |
+
|
168 |
+
|
169 |
+
### Framework versions
|
170 |
+
|
171 |
+
- Transformers 4.16.0.dev0
|
172 |
+
- Pytorch 1.10.1+cu102
|
173 |
+
- Datasets 1.17.1.dev0
|
174 |
+
- Tokenizers 0.11.0
|