%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
20220413 210552
2
20220413 210552
Developed by lilitket
This model is a fine-tuned speech recognition model based on facebook/wav2vec2-xls-r-300m on the common_voice dataset
Downloads 18
Release Time : 4/13/2022
Model Overview
This is a fine-tuned model for speech recognition, based on the wav2vec2-xls-r-300m architecture, trained on the common_voice dataset.
Model Features
Efficient Fine-tuning
Fine-tuned based on the powerful wav2vec2-xls-r-300m base model
Low Word Error Rate
Achieved a word error rate (WER) of 1.0006 on the evaluation set
Optimized Training
Utilized linear learning rate scheduling and 2000-step warm-up training
Model Capabilities
Speech-to-Text
Automatic Speech Recognition
Use Cases
Speech Transcription
Speech to Text
Convert speech content into text transcripts
Word error rate 1.0006
đ 20220413-210552
This model is a fine - tuned version of facebook/wav2vec2 - xls - r - 300m on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 3.0348
- Wer: 1.0006
đ Quick Start
This model is a fine - tuned speech recognition model. You can use it for speech - related tasks based on the pre - trained model facebook/wav2vec2 - xls - r - 300m.
đ Documentation
Model description
This model is a fine - tuned version of facebook/wav2vec2 - xls - r - 300m on the common_voice dataset.
Intended uses & limitations
No specific information provided yet.
Training and evaluation data
No specific information provided yet.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 6e - 06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- num_epochs: 1200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 17.1111 | 1.5 | 200 | 16.6792 | 1.0 |
| 16.0992 | 3.01 | 400 | 15.3947 | 1.0 |
| 10.7668 | 4.51 | 600 | 10.3625 | 1.0 |
| 6.2652 | 6.02 | 800 | 7.6849 | 1.0 |
| 5.1417 | 7.52 | 1000 | 6.0307 | 1.0 |
| 4.6159 | 9.02 | 1200 | 5.0891 | 1.0 |
| 4.2444 | 10.53 | 1400 | 4.4120 | 1.0 |
| 3.8935 | 12.03 | 1600 | 3.9570 | 1.0 |
| 3.6292 | 13.53 | 1800 | 3.6405 | 1.0 |
| 3.4535 | 15.04 | 2000 | 3.4523 | 1.0 |
| 3.3175 | 16.54 | 2200 | 3.3589 | 1.0 |
| 3.2266 | 18.05 | 2400 | 3.2966 | 1.0 |
| 3.1825 | 19.55 | 2600 | 3.2658 | 1.0 |
| 3.1604 | 21.05 | 2800 | 3.2534 | 1.0 |
| 3.1438 | 22.56 | 3000 | 3.2437 | 1.0 |
| 3.1176 | 24.06 | 3200 | 3.2169 | 1.0 |
| 3.1088 | 25.56 | 3400 | 3.2102 | 1.0 |
| 3.0955 | 27.07 | 3600 | 3.1983 | 1.0 |
| 3.0763 | 28.57 | 3800 | 3.2092 | 1.0 |
| 3.0599 | 30.08 | 4000 | 3.2092 | 1.0 |
| 3.0385 | 31.58 | 4200 | 3.2154 | 1.0 |
| 2.9996 | 33.08 | 4400 | 3.2120 | 1.0 |
| 2.9207 | 34.59 | 4600 | 3.2146 | 1.0 |
| 2.8071 | 36.09 | 4800 | 3.2093 | 1.0 |
| 2.6412 | 37.59 | 5000 | 3.2282 | 1.0 |
| 2.4594 | 39.1 | 5200 | 3.2442 | 1.0 |
| 2.2708 | 40.6 | 5400 | 3.2944 | 1.0 |
| 2.1279 | 42.11 | 5600 | 3.3260 | 1.0 |
| 1.9985 | 43.61 | 5800 | 3.3586 | 1.0 |
| 1.8979 | 45.11 | 6000 | 3.3945 | 1.0 |
| 1.7838 | 46.62 | 6200 | 3.4761 | 1.0 |
| 1.6774 | 48.12 | 6400 | 3.4886 | 1.0 |
| 1.5958 | 49.62 | 6600 | 3.6208 | 1.0 |
| 1.4957 | 51.13 | 6800 | 3.6501 | 1.0 |
| 1.4202 | 52.63 | 7000 | 3.6492 | 1.0 |
| 1.3377 | 54.14 | 7200 | 3.7392 | 1.0 |
| 1.2872 | 55.64 | 7400 | 3.8624 | 1.0 |
| 1.1992 | 57.14 | 7600 | 3.8511 | 1.0 |
| 1.1238 | 58.65 | 7800 | 3.9662 | 1.0 |
| 1.0775 | 60.15 | 8000 | 3.9267 | 1.0 |
| 1.011 | 61.65 | 8200 | 4.0933 | 1.0 |
| 0.962 | 63.16 | 8400 | 4.0941 | 1.0 |
| 0.9041 | 64.66 | 8600 | 4.1163 | 1.0 |
| 0.8552 | 66.17 | 8800 | 4.1937 | 1.0 |
| 0.8054 | 67.67 | 9000 | 4.2277 | 1.0 |
| 0.7457 | 69.17 | 9200 | 4.3899 | 1.0 |
| 0.7292 | 70.68 | 9400 | 4.3621 | 1.0 |
| 0.6635 | 72.18 | 9600 | 4.4706 | 1.0 |
| 0.6333 | 73.68 | 9800 | 4.4571 | 1.0 |
| 0.6109 | 75.19 | 10000 | 4.4594 | 1.0 |
| 0.5611 | 76.69 | 10200 | 4.5672 | 1.0 |
| 0.5286 | 78.2 | 10400 | 4.4957 | 1.0 |
| 0.4894 | 79.7 | 10600 | 4.5278 | 1.0 |
| 0.4831 | 81.2 | 10800 | 4.4604 | 1.0 |
| 0.4575 | 82.71 | 11000 | 4.7439 | 1.0 |
| 0.4418 | 84.21 | 11200 | 4.6511 | 1.0 |
| 0.4085 | 85.71 | 11400 | 4.5008 | 1.0 |
| 0.4011 | 87.22 | 11600 | 4.7690 | 1.0 |
| 0.3791 | 88.72 | 11800 | 4.8675 | 1.0 |
| 0.3487 | 90.23 | 12000 | 5.0327 | 1.0 |
| 0.3661 | 91.73 | 12200 | 4.8084 | 1.0 |
| 0.3306 | 93.23 | 12400 | 4.9095 | 1.0 |
| 0.3449 | 94.74 | 12600 | 4.8223 | 1.0 |
| 0.2949 | 96.24 | 12800 | 4.8245 | 1.0 |
| 0.2987 | 97.74 | 13000 | 5.0803 | 1.0 |
| 0.2896 | 99.25 | 13200 | 5.2074 | 1.0 |
| 0.2731 | 100.75 | 13400 | 5.1951 | 1.0 |
| 0.2749 | 102.26 | 13600 | 5.2071 | 1.0 |
| 0.2554 | 103.76 | 13800 | 5.0861 | 1.0 |
| 0.2436 | 105.26 | 14000 | 5.0851 | 1.0 |
| 0.2494 | 106.77 | 14200 | 4.8623 | 1.0 |
| 0.23 | 108.27 | 14400 | 5.0466 | 1.0 |
| 0.2345 | 109.77 | 14600 | 5.2474 | 1.0 |
| 0.2233 | 111.28 | 14800 | 4.9394 | 1.0 |
| 0.2231 | 112.78 | 15000 | 4.9572 | 1.0 |
| 0.213 | 114.29 | 15200 | 5.3215 | 1.0 |
| 0.2002 | 115.79 | 15400 | 5.3042 | 1.0 |
| 0.2023 | 117.29 | 15600 | 5.0279 | 1.0 |
| 0.2074 | 118.8 | 15800 | 4.9727 | 1.0 |
| 0.2071 | 120.3 | 16000 | 4.6775 | 1.0 |
| 0.1915 | 121.8 | 16200 | 4.8386 | 1.0 |
| 0.1899 | 123.31 | 16400 | 4.7898 | 1.0 |
| 0.1821 | 124.81 | 16600 | 5.3147 | 1.0 |
| 0.1908 | 126.32 | 16800 | 5.6218 | 1.0 |
| 0.1712 | 127.82 | 17000 | 4.6083 | 1.0 |
| 0.1705 | 129.32 | 17200 | 5.2468 | 1.0 |
| 0.1664 | 130.83 | 17400 | 5.0412 | 1.0 |
| 0.167 | 132.33 | 17600 | 5.0116 | 1.0 |
| 0.162 | 133.83 | 17800 | 5.2799 | 1.0 |
| 0.1561 | 135.34 | 18000 | 5.2485 | 1.0 |
| 0.1501 | 136.84 | 18200 | 5.1109 | 1.0 |
| 0.14 | 138.35 | 18400 | 5.2310 | 1.0 |
| 0.1576 | 139.85 | 18600 | 5.1631 | 1.0 |
| 0.1433 | 141.35 | 18800 | 5.3497 | 1.0 |
| 0.148 | 142.86 | 19000 | 4.8892 | 1.0 |
| 0.1525 | 144.36 | 19200 | 4.8522 | 1.0 |
| 0.1517 | 145.86 | 19400 | 4.7830 | 1.0 |
| 0.139 | 147.37 | 19600 | 5.2041 | 1.0 |
| 0.1392 | 148.87 | 19800 | 4.7968 | 1.0 |
| 0.1351 | 150.38 | 20000 | 5.0326 | 1.0 |
| 0.1355 | 151.88 | 20200 | 5.0474 | 1.0 |
| 0.138 | 153.38 | 20400 | 4.7491 | 1.0006 |
| 0.1332 | 154.89 | 20600 | 5.3905 | 1.0 |
| 0.1252 | 156.39 | 20800 | 4.9815 | 1.0 |
| 0.1179 | 157.89 | 21000 | 5.3281 | 1.0 |
| 0.1228 | 159.4 | 21200 | 5.1108 | 1.0006 |
| 0.1311 | 160.9 | 21400 | 4.8016 | 1.0 |
| 0.1278 | 162.41 | 21600 | 4.8306 | 1.0 |
| 0.1209 | 163.91 | 21800 | 4.6413 | 1.0 |
| 0.1199 | 165.41 | 22000 | 4.6375 | 1.0 |
| 0.1172 | 166.92 | 22200 | 4.9108 | 1.0 |
| 0.1247 | 168.42 | 22400 | 4.6139 | 1.0006 |
| 0.1121 | 169.92 | 22600 | 4.4765 | 1.0006 |
| 0.125 | 171.43 | 22800 | 4.6819 | 1.0006 |
| 0.1259 | 172.93 | 23000 | 4.9577 | 1.0 |
| 0.1044 | 174.44 | 23200 | 5.2993 | 1.0006 |
| 0.1107 | 175.94 | 23400 | 4.3140 | 1.0 |
| 0.1142 | 177.44 | 23600 | 4.5850 | 1.0 |
| 0.0971 | 178.95 | 23800 | 4.8177 | 1.0006 |
| 0.1186 | 180.45 | 24000 | 4.9972 | 1.0 |
| 0.1164 | 181.95 | 24200 | 4.5840 | 1.0 |
| 0.1014 | 183.46 | 24400 | 4.9117 | 0.9994 |
| 0.1087 | 184.96 | 24600 | 4.5646 | 1.0006 |
| 0.1075 | 186.47 | 24800 | 4.6995 | 1.0 |
| 0.1111 | 187.97 | 25000 | 4.7877 | 1.0 |
| 0.1079 | 189.47 | 25200 | 4.8420 | 1.0 |
| 0.1053 | 190.98 | 25400 | 5.1083 | 1.0 |
| 0.1048 | 192.48 | 25600 | 4.2876 | 1.0 |
| 0.0974 | 193.98 | 25800 | 4.6699 | 1.0006 |
| 0.0983 | 195.49 | 26000 | 4.6522 | 1.0 |
| 0.0935 | 196.99 | 26200 | 4.9879 | 1.0 |
| 0.0948 | 198.5 | 26400 | 4.4146 | 1.0 |
| 0.0867 | 200.0 | 26600 | 5.1909 | 1.0 |
| 0.0932 | 201.5 | 26800 | 5.2019 | 1.0 |
| 0.0951 | 203.01 | 27000 | 3.6893 | 1.0 |
| 0.085 | 204.51 | 27200 | 4.3071 | 1.0006 |
| 0.0912 | 206.02 | 27400 | 4.4651 | 1.0 |
| 0.092 | 207.52 | 27600 | 4.4218 | 1.0 |
| 0.0936 | 209.02 | 27800 | 5.1391 | 1.0 |
| 0.0989 | 210.53 | 28000 | 4.8787 | 1.0006 |
| 0.0898 | 212.03 | 28200 | 4.1418 | 1.0013 |
| 0.0943 | 213.53 | 28400 | 4.1857 | 1.0 |
| 0.0834 | 215.04 | 28600 | 4.3519 | 1.0 |
| 0.0851 | 216.54 | 28800 | 4.3612 | 1.0006 |
| 0.0932 | 218.05 | 29000 | 4.2200 | 1.0006 |
| 0.0848 | 219.55 | 29200 | 4.2054 | 1.0 |
| 0.0873 | 221.05 | 29400 | 4.4815 | 1.0 |
| 0.0949 | 222.56 | 29600 | 3.9426 | 1.0 |
| 0.0856 | 224.06 | 29800 | 3.7650 | 1.0 |
| 0.0768 | 225.56 | 30000 | 3.9774 | 1.0 |
| 0.0823 | 227.07 | 30200 | 4.3728 | 1.0 |
| 0.0913 | 228.57 | 30400 | 3.7813 | 1.0 |
| 0.0951 | 230.08 | 30600 | 4.1581 | 1.0 |
| 0.0843 | 231.58 | 30800 | 4.6891 | 1.0 |
| 0.0879 | 233.08 | 31000 | 4.2984 | 1.0 |
| 0.0807 | 234.59 | 31200 | 3.9511 | 1.0 |
| 0.0765 | 236.09 | 31400 | 3.8094 | 1.0 |
| 0.0861 | 237.59 | 31600 | 4.3118 | 1.0 |
| 0.0596 | 239.1 | 31800 | 4.0774 | 1.0006 |
| 0.0752 | 240.6 | 32000 | 3.6005 | 1.0 |
| 0.0729 | 242.11 | 32200 | 4.8616 | 1.0 |
| 0.0783 | 243.61 | 32400 | 3.9858 | 1.0 |
| 0.0759 | 245.11 | 32600 | 4.1231 | 1.0 |
| 0.08 | 246.62 | 32800 | 4.5182 | 1.0 |
| 0.0782 | 248.12 | 33000 | 3.7721 | 1.0 |
| 0.0914 | 249.62 | 33200 | 3.5902 | 1.0 |
| 0.0668 | 251.13 | 33400 | 3.9673 | 1.0 |
| 0.0798 | 252.63 | 33600 | 3.8693 | 1.0 |
| 0.0814 | 254.14 | 33800 | 3.9804 | 1.0006 |
| 0.0775 | 255.64 | 34000 | 3.9483 | 1.0 |
| 0.0721 | 257.14 | 34200 | 4.6892 | 1.0 |
| 0.0722 | 258.65 | 34400 | 4.1972 | 1.0 |
| 0.0755 | 260.15 | 34600 | 4.4523 | 1.0 |
| 0.0683 | 261.65 | 34800 | 4.1090 | 1.0 |
| 0.0698 | 263.16 | 35000 | 4.0634 | 1.0 |
| 0.0712 | 264.66 | 35200 | 4.0469 | 1.0006 |
| 0.0754 | 266.17 | 35400 | 4.0113 | 1.0006 |
| 0.0709 | 267.67 | 35600 | 4.0592 | 1.0 |
| 0.0637 | 269.17 | 35800 | 3.7540 | 1.0 |
| 0.0688 | 270.68 | 36000 | 3.9645 | 1.0 |
| 0.0592 | 272.18 | 36200 | 3.7443 | 1.0 |
| 0.0585 | 273.68 | 36400 | 3.8287 | 1.0 |
| 0.0734 | 275.19 | 36600 | 3.6780 | 1.0 |
| 0.058 | 276.69 | 36800 | 3.7384 | 1.0 |
| 0.057 | 278.2 | 37000 | 3.7384 | 1.0 |
| 0.055 | 279.7 | 37200 | 3.7384 | 1.0 |
| 0.053 | 281.21 | 37400 | 3.7384 | 1.0 |
| 0.051 | 282.71 | 37600 | 3.7384 | 1.0 |
| 0.049 | 284.22 | 37800 | 3.7384 | 1.0 |
| 0.047 | 285.72 | 38000 | 3.7384 | 1.0 |
| 0.045 | 287.22 | 38200 | 3.7384 | 1.0 |
| 0.043 | 288.73 | 38400 | 3.7384 | 1.0 |
| 0.041 | 290.23 | 38600 | 3.7384 | 1.0 |
| 0.039 | 291.74 | 38800 | 3.7384 | 1.0 |
| 0.037 | 293.24 | 39000 | 3.7384 | 1.0 |
| 0.035 | 294.74 | 39200 | 3.7384 | 1.0 |
| 0.033 | 296.25 | 39400 | 3.7384 | 1.0 |
| 0.031 | 297.75 | 39600 | 3.7384 | 1.0 |
| 0.029 | 299.26 | 39800 | 3.7384 | 1.0 |
| 0.027 | 300.76 | 40000 | 3.7384 | 1.0 |
đ License
This project is licensed under the Apache - 2.0 license.
Voice Activity Detection
MIT
Voice activity detection model based on pyannote.audio 2.1, used to identify speech activity segments in audio
Speech Recognition
V
pyannote
7.7M
181
Wav2vec2 Large Xlsr 53 Portuguese
Apache-2.0
This is a fine-tuned XLSR-53 large model for Portuguese speech recognition tasks, trained on the Common Voice 6.1 dataset, supporting Portuguese speech-to-text conversion.
Speech Recognition Other
W
jonatasgrosman
4.9M
32
Whisper Large V3
Apache-2.0
Whisper is an advanced automatic speech recognition (ASR) and speech translation model proposed by OpenAI, trained on over 5 million hours of labeled data, with strong cross-dataset and cross-domain generalization capabilities.
Speech Recognition Supports Multiple Languages
W
openai
4.6M
4,321
Whisper Large V3 Turbo
MIT
Whisper is a state-of-the-art automatic speech recognition (ASR) and speech translation model developed by OpenAI, trained on over 5 million hours of labeled data, demonstrating strong generalization capabilities in zero-shot settings.
Speech Recognition
Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesW
openai
4.0M
2,317
Wav2vec2 Large Xlsr 53 Russian
Apache-2.0
A Russian speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, supporting 16kHz sampled audio input
Speech Recognition Other
W
jonatasgrosman
3.9M
54
Wav2vec2 Large Xlsr 53 Chinese Zh Cn
Apache-2.0
A Chinese speech recognition model fine-tuned based on facebook/wav2vec2-large-xlsr-53, supporting 16kHz sampling rate audio input.
Speech Recognition Chinese
W
jonatasgrosman
3.8M
110
Wav2vec2 Large Xlsr 53 Dutch
Apache-2.0
A Dutch speech recognition model fine-tuned based on facebook/wav2vec2-large-xlsr-53, trained on the Common Voice and CSS10 datasets, supporting 16kHz audio input.
Speech Recognition Other
W
jonatasgrosman
3.0M
12
Wav2vec2 Large Xlsr 53 Japanese
Apache-2.0
Japanese speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, supporting 16kHz sampling rate audio input
Speech Recognition Japanese
W
jonatasgrosman
2.9M
33
Mms 300m 1130 Forced Aligner
A text-to-audio forced alignment tool based on Hugging Face pre-trained models, supporting multiple languages with high memory efficiency
Speech Recognition Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesM
MahmoudAshraf
2.5M
50
Wav2vec2 Large Xlsr 53 Arabic
Apache-2.0
Arabic speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, trained on Common Voice and Arabic speech corpus
Speech Recognition Arabic
W
jonatasgrosman
2.3M
37
Featured Recommended AI Models
Š 2025AIbase