update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,216 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-large-xls-r-300m-tr
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# wav2vec2-large-xls-r-300m-tr
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2223
|
| 20 |
+
- Wer: 0.2867
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 2e-05
|
| 40 |
+
- train_batch_size: 32
|
| 41 |
+
- eval_batch_size: 32
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 500
|
| 46 |
+
- num_epochs: 100.0
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 53 |
+
| 6.8222 | 0.64 | 500 | 3.5026 | 1.0 |
|
| 54 |
+
| 3.2136 | 1.28 | 1000 | 3.0593 | 1.0000 |
|
| 55 |
+
| 2.8882 | 1.91 | 1500 | 2.4670 | 0.9939 |
|
| 56 |
+
| 2.3743 | 2.55 | 2000 | 1.1844 | 0.8657 |
|
| 57 |
+
| 1.9456 | 3.19 | 2500 | 0.8228 | 0.7397 |
|
| 58 |
+
| 1.7781 | 3.83 | 3000 | 0.6826 | 0.6753 |
|
| 59 |
+
| 1.6848 | 4.46 | 3500 | 0.5885 | 0.6140 |
|
| 60 |
+
| 1.6228 | 5.1 | 4000 | 0.5274 | 0.5789 |
|
| 61 |
+
| 1.5768 | 5.74 | 4500 | 0.4900 | 0.5519 |
|
| 62 |
+
| 1.5431 | 6.38 | 5000 | 0.4508 | 0.5238 |
|
| 63 |
+
| 1.5019 | 7.02 | 5500 | 0.4248 | 0.5021 |
|
| 64 |
+
| 1.4684 | 7.65 | 6000 | 0.4009 | 0.4827 |
|
| 65 |
+
| 1.4635 | 8.29 | 6500 | 0.3830 | 0.4700 |
|
| 66 |
+
| 1.4291 | 8.93 | 7000 | 0.3707 | 0.4595 |
|
| 67 |
+
| 1.4271 | 9.57 | 7500 | 0.3570 | 0.4514 |
|
| 68 |
+
| 1.3938 | 10.2 | 8000 | 0.3479 | 0.4378 |
|
| 69 |
+
| 1.3914 | 10.84 | 8500 | 0.3396 | 0.4368 |
|
| 70 |
+
| 1.3767 | 11.48 | 9000 | 0.3253 | 0.4262 |
|
| 71 |
+
| 1.3641 | 12.12 | 9500 | 0.3251 | 0.4178 |
|
| 72 |
+
| 1.355 | 12.76 | 10000 | 0.3138 | 0.4136 |
|
| 73 |
+
| 1.336 | 13.39 | 10500 | 0.3121 | 0.4069 |
|
| 74 |
+
| 1.3292 | 14.03 | 11000 | 0.3041 | 0.4014 |
|
| 75 |
+
| 1.3249 | 14.67 | 11500 | 0.3014 | 0.3931 |
|
| 76 |
+
| 1.3156 | 15.31 | 12000 | 0.3014 | 0.3929 |
|
| 77 |
+
| 1.313 | 15.94 | 12500 | 0.2969 | 0.3968 |
|
| 78 |
+
| 1.3068 | 16.58 | 13000 | 0.2965 | 0.3966 |
|
| 79 |
+
| 1.2785 | 17.22 | 13500 | 0.2943 | 0.3850 |
|
| 80 |
+
| 1.2867 | 17.86 | 14000 | 0.2912 | 0.3782 |
|
| 81 |
+
| 1.2714 | 18.49 | 14500 | 0.2819 | 0.3747 |
|
| 82 |
+
| 1.2844 | 19.13 | 15000 | 0.2840 | 0.3740 |
|
| 83 |
+
| 1.2684 | 19.77 | 15500 | 0.2913 | 0.3828 |
|
| 84 |
+
| 1.26 | 20.41 | 16000 | 0.2739 | 0.3674 |
|
| 85 |
+
| 1.2543 | 21.05 | 16500 | 0.2740 | 0.3691 |
|
| 86 |
+
| 1.2532 | 21.68 | 17000 | 0.2709 | 0.3756 |
|
| 87 |
+
| 1.2409 | 22.32 | 17500 | 0.2669 | 0.3593 |
|
| 88 |
+
| 1.2404 | 22.96 | 18000 | 0.2673 | 0.3576 |
|
| 89 |
+
| 1.2347 | 23.6 | 18500 | 0.2678 | 0.3643 |
|
| 90 |
+
| 1.2351 | 24.23 | 19000 | 0.2715 | 0.3650 |
|
| 91 |
+
| 1.2409 | 24.87 | 19500 | 0.2637 | 0.3571 |
|
| 92 |
+
| 1.2152 | 25.51 | 20000 | 0.2785 | 0.3609 |
|
| 93 |
+
| 1.2046 | 26.15 | 20500 | 0.2610 | 0.3508 |
|
| 94 |
+
| 1.2082 | 26.79 | 21000 | 0.2619 | 0.3461 |
|
| 95 |
+
| 1.2109 | 27.42 | 21500 | 0.2597 | 0.3502 |
|
| 96 |
+
| 1.2014 | 28.06 | 22000 | 0.2608 | 0.3468 |
|
| 97 |
+
| 1.1948 | 28.7 | 22500 | 0.2573 | 0.3457 |
|
| 98 |
+
| 1.205 | 29.34 | 23000 | 0.2619 | 0.3464 |
|
| 99 |
+
| 1.2019 | 29.97 | 23500 | 0.2559 | 0.3474 |
|
| 100 |
+
| 1.1917 | 30.61 | 24000 | 0.2601 | 0.3462 |
|
| 101 |
+
| 1.1939 | 31.25 | 24500 | 0.2575 | 0.3387 |
|
| 102 |
+
| 1.1882 | 31.89 | 25000 | 0.2535 | 0.3368 |
|
| 103 |
+
| 1.191 | 32.53 | 25500 | 0.2489 | 0.3365 |
|
| 104 |
+
| 1.1767 | 33.16 | 26000 | 0.2501 | 0.3347 |
|
| 105 |
+
| 1.167 | 33.8 | 26500 | 0.2504 | 0.3347 |
|
| 106 |
+
| 1.1678 | 34.44 | 27000 | 0.2480 | 0.3378 |
|
| 107 |
+
| 1.1803 | 35.08 | 27500 | 0.2487 | 0.3345 |
|
| 108 |
+
| 1.167 | 35.71 | 28000 | 0.2442 | 0.3319 |
|
| 109 |
+
| 1.1661 | 36.35 | 28500 | 0.2495 | 0.3334 |
|
| 110 |
+
| 1.164 | 36.99 | 29000 | 0.2472 | 0.3292 |
|
| 111 |
+
| 1.1578 | 37.63 | 29500 | 0.2442 | 0.3242 |
|
| 112 |
+
| 1.1584 | 38.27 | 30000 | 0.2431 | 0.3314 |
|
| 113 |
+
| 1.1526 | 38.9 | 30500 | 0.2441 | 0.3347 |
|
| 114 |
+
| 1.1542 | 39.54 | 31000 | 0.2437 | 0.3330 |
|
| 115 |
+
| 1.1508 | 40.18 | 31500 | 0.2433 | 0.3294 |
|
| 116 |
+
| 1.1406 | 40.82 | 32000 | 0.2434 | 0.3271 |
|
| 117 |
+
| 1.1514 | 41.45 | 32500 | 0.2426 | 0.3255 |
|
| 118 |
+
| 1.1418 | 42.09 | 33000 | 0.2432 | 0.3233 |
|
| 119 |
+
| 1.1365 | 42.73 | 33500 | 0.2436 | 0.3240 |
|
| 120 |
+
| 1.1348 | 43.37 | 34000 | 0.2483 | 0.3257 |
|
| 121 |
+
| 1.1301 | 44.01 | 34500 | 0.2420 | 0.3271 |
|
| 122 |
+
| 1.1268 | 44.64 | 35000 | 0.2472 | 0.3225 |
|
| 123 |
+
| 1.1224 | 45.28 | 35500 | 0.2382 | 0.3205 |
|
| 124 |
+
| 1.1224 | 45.92 | 36000 | 0.2388 | 0.3184 |
|
| 125 |
+
| 1.1198 | 46.56 | 36500 | 0.2382 | 0.3202 |
|
| 126 |
+
| 1.1274 | 47.19 | 37000 | 0.2404 | 0.3172 |
|
| 127 |
+
| 1.1147 | 47.83 | 37500 | 0.2394 | 0.3164 |
|
| 128 |
+
| 1.121 | 48.47 | 38000 | 0.2406 | 0.3202 |
|
| 129 |
+
| 1.1109 | 49.11 | 38500 | 0.2384 | 0.3154 |
|
| 130 |
+
| 1.1164 | 49.74 | 39000 | 0.2375 | 0.3169 |
|
| 131 |
+
| 1.1105 | 50.38 | 39500 | 0.2387 | 0.3173 |
|
| 132 |
+
| 1.1054 | 51.02 | 40000 | 0.2362 | 0.3120 |
|
| 133 |
+
| 1.0893 | 51.66 | 40500 | 0.2399 | 0.3130 |
|
| 134 |
+
| 1.0913 | 52.3 | 41000 | 0.2357 | 0.3088 |
|
| 135 |
+
| 1.1017 | 52.93 | 41500 | 0.2345 | 0.3084 |
|
| 136 |
+
| 1.0937 | 53.57 | 42000 | 0.2330 | 0.3140 |
|
| 137 |
+
| 1.0945 | 54.21 | 42500 | 0.2399 | 0.3107 |
|
| 138 |
+
| 1.0933 | 54.85 | 43000 | 0.2383 | 0.3134 |
|
| 139 |
+
| 1.0912 | 55.48 | 43500 | 0.2372 | 0.3077 |
|
| 140 |
+
| 1.0898 | 56.12 | 44000 | 0.2339 | 0.3083 |
|
| 141 |
+
| 1.0903 | 56.76 | 44500 | 0.2367 | 0.3065 |
|
| 142 |
+
| 1.0947 | 57.4 | 45000 | 0.2352 | 0.3104 |
|
| 143 |
+
| 1.0751 | 58.04 | 45500 | 0.2334 | 0.3084 |
|
| 144 |
+
| 1.09 | 58.67 | 46000 | 0.2328 | 0.3100 |
|
| 145 |
+
| 1.0876 | 59.31 | 46500 | 0.2276 | 0.3050 |
|
| 146 |
+
| 1.076 | 59.95 | 47000 | 0.2309 | 0.3047 |
|
| 147 |
+
| 1.086 | 60.59 | 47500 | 0.2293 | 0.3047 |
|
| 148 |
+
| 1.082 | 61.22 | 48000 | 0.2328 | 0.3027 |
|
| 149 |
+
| 1.0714 | 61.86 | 48500 | 0.2290 | 0.3020 |
|
| 150 |
+
| 1.0746 | 62.5 | 49000 | 0.2313 | 0.3059 |
|
| 151 |
+
| 1.076 | 63.14 | 49500 | 0.2342 | 0.3050 |
|
| 152 |
+
| 1.0648 | 63.78 | 50000 | 0.2286 | 0.3025 |
|
| 153 |
+
| 1.0586 | 64.41 | 50500 | 0.2338 | 0.3044 |
|
| 154 |
+
| 1.0753 | 65.05 | 51000 | 0.2308 | 0.3045 |
|
| 155 |
+
| 1.0664 | 65.69 | 51500 | 0.2273 | 0.3009 |
|
| 156 |
+
| 1.0739 | 66.33 | 52000 | 0.2298 | 0.3027 |
|
| 157 |
+
| 1.0695 | 66.96 | 52500 | 0.2247 | 0.2996 |
|
| 158 |
+
| 1.06 | 67.6 | 53000 | 0.2276 | 0.3015 |
|
| 159 |
+
| 1.0742 | 68.24 | 53500 | 0.2280 | 0.2974 |
|
| 160 |
+
| 1.0618 | 68.88 | 54000 | 0.2291 | 0.2989 |
|
| 161 |
+
| 1.062 | 69.52 | 54500 | 0.2302 | 0.2971 |
|
| 162 |
+
| 1.0572 | 70.15 | 55000 | 0.2280 | 0.2990 |
|
| 163 |
+
| 1.055 | 70.79 | 55500 | 0.2278 | 0.2983 |
|
| 164 |
+
| 1.0553 | 71.43 | 56000 | 0.2282 | 0.2991 |
|
| 165 |
+
| 1.0509 | 72.07 | 56500 | 0.2261 | 0.2959 |
|
| 166 |
+
| 1.0469 | 72.7 | 57000 | 0.2216 | 0.2919 |
|
| 167 |
+
| 1.0476 | 73.34 | 57500 | 0.2267 | 0.2989 |
|
| 168 |
+
| 1.0494 | 73.98 | 58000 | 0.2260 | 0.2960 |
|
| 169 |
+
| 1.0517 | 74.62 | 58500 | 0.2297 | 0.2989 |
|
| 170 |
+
| 1.0458 | 75.26 | 59000 | 0.2246 | 0.2923 |
|
| 171 |
+
| 1.0382 | 75.89 | 59500 | 0.2255 | 0.2922 |
|
| 172 |
+
| 1.0462 | 76.53 | 60000 | 0.2258 | 0.2954 |
|
| 173 |
+
| 1.0375 | 77.17 | 60500 | 0.2251 | 0.2929 |
|
| 174 |
+
| 1.0332 | 77.81 | 61000 | 0.2277 | 0.2940 |
|
| 175 |
+
| 1.0423 | 78.44 | 61500 | 0.2243 | 0.2896 |
|
| 176 |
+
| 1.0379 | 79.08 | 62000 | 0.2274 | 0.2928 |
|
| 177 |
+
| 1.0398 | 79.72 | 62500 | 0.2237 | 0.2928 |
|
| 178 |
+
| 1.0395 | 80.36 | 63000 | 0.2265 | 0.2956 |
|
| 179 |
+
| 1.0397 | 80.99 | 63500 | 0.2240 | 0.2920 |
|
| 180 |
+
| 1.0262 | 81.63 | 64000 | 0.2244 | 0.2934 |
|
| 181 |
+
| 1.0335 | 82.27 | 64500 | 0.2265 | 0.2936 |
|
| 182 |
+
| 1.0385 | 82.91 | 65000 | 0.2238 | 0.2928 |
|
| 183 |
+
| 1.0289 | 83.55 | 65500 | 0.2219 | 0.2912 |
|
| 184 |
+
| 1.0372 | 84.18 | 66000 | 0.2236 | 0.2898 |
|
| 185 |
+
| 1.0279 | 84.82 | 66500 | 0.2219 | 0.2902 |
|
| 186 |
+
| 1.0325 | 85.46 | 67000 | 0.2240 | 0.2908 |
|
| 187 |
+
| 1.0202 | 86.1 | 67500 | 0.2206 | 0.2886 |
|
| 188 |
+
| 1.0166 | 86.73 | 68000 | 0.2219 | 0.2886 |
|
| 189 |
+
| 1.0259 | 87.37 | 68500 | 0.2235 | 0.2897 |
|
| 190 |
+
| 1.0337 | 88.01 | 69000 | 0.2210 | 0.2873 |
|
| 191 |
+
| 1.0264 | 88.65 | 69500 | 0.2216 | 0.2882 |
|
| 192 |
+
| 1.0231 | 89.29 | 70000 | 0.2223 | 0.2899 |
|
| 193 |
+
| 1.0281 | 89.92 | 70500 | 0.2214 | 0.2872 |
|
| 194 |
+
| 1.0135 | 90.56 | 71000 | 0.2218 | 0.2868 |
|
| 195 |
+
| 1.0291 | 91.2 | 71500 | 0.2209 | 0.2863 |
|
| 196 |
+
| 1.0321 | 91.84 | 72000 | 0.2199 | 0.2876 |
|
| 197 |
+
| 1.028 | 92.47 | 72500 | 0.2214 | 0.2858 |
|
| 198 |
+
| 1.0213 | 93.11 | 73000 | 0.2219 | 0.2875 |
|
| 199 |
+
| 1.0261 | 93.75 | 73500 | 0.2232 | 0.2869 |
|
| 200 |
+
| 1.0197 | 94.39 | 74000 | 0.2227 | 0.2866 |
|
| 201 |
+
| 1.0298 | 95.03 | 74500 | 0.2228 | 0.2868 |
|
| 202 |
+
| 1.0192 | 95.66 | 75000 | 0.2230 | 0.2865 |
|
| 203 |
+
| 1.0156 | 96.3 | 75500 | 0.2220 | 0.2869 |
|
| 204 |
+
| 1.0075 | 96.94 | 76000 | 0.2223 | 0.2866 |
|
| 205 |
+
| 1.0201 | 97.58 | 76500 | 0.2219 | 0.2866 |
|
| 206 |
+
| 1.0159 | 98.21 | 77000 | 0.2219 | 0.2876 |
|
| 207 |
+
| 1.0087 | 98.85 | 77500 | 0.2219 | 0.2873 |
|
| 208 |
+
| 1.0159 | 99.49 | 78000 | 0.2223 | 0.2867 |
|
| 209 |
+
|
| 210 |
+
|
| 211 |
+
### Framework versions
|
| 212 |
+
|
| 213 |
+
- Transformers 4.17.0.dev0
|
| 214 |
+
- Pytorch 1.10.2+cu102
|
| 215 |
+
- Datasets 1.18.2.dev0
|
| 216 |
+
- Tokenizers 0.11.0
|