DrishtiSharma / wav2vec2-xls-r-sl-a2

huggingface.co
Total runs: 23
24-hour runs: 0
7-day runs: -77
30-day runs: -69
Model's Last Updated: March 24 2022
automatic-speech-recognition

Introduction of wav2vec2-xls-r-sl-a2

Model Details of wav2vec2-xls-r-sl-a2

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - SL dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2855
  • Wer: 0.2401

##Evaluation Commands

  1. To evaluate on mozilla-foundation/common_voice_8_0 with test split

python eval.py --model_id DrishtiSharma/wav2vec2-xls-r-sl-a2 --dataset mozilla-foundation/common_voice_8_0 --config sl --split test --log_outputs

  1. To evaluate on speech-recognition-community-v2/dev_data

Votic language not found in speech-recognition-community-v2/dev_data

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 7e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 100.0
  • mixed_precision_training: Native AMP
Training results
Training Loss Epoch Step Validation Loss Wer
6.9294 6.1 500 2.9712 1.0
2.8305 12.2 1000 1.7073 0.9479
1.4795 18.29 1500 0.5756 0.6397
1.3433 24.39 2000 0.4968 0.5424
1.1766 30.49 2500 0.4185 0.4743
1.0017 36.59 3000 0.3303 0.3578
0.9358 42.68 3500 0.3003 0.3051
0.8358 48.78 4000 0.3045 0.2884
0.7647 54.88 4500 0.2866 0.2677
0.7482 60.98 5000 0.2829 0.2585
0.6943 67.07 5500 0.2782 0.2478
0.6586 73.17 6000 0.2911 0.2537
0.6425 79.27 6500 0.2817 0.2462
0.6067 85.37 7000 0.2910 0.2436
0.5974 91.46 7500 0.2875 0.2430
0.5812 97.56 8000 0.2852 0.2396
Framework versions
  • Transformers 4.17.0.dev0
  • Pytorch 1.10.2+cu102
  • Datasets 1.18.2.dev0
  • Tokenizers 0.11.0

Runs of DrishtiSharma wav2vec2-xls-r-sl-a2 on huggingface.co

23
Total runs
0
24-hour runs
0
3-day runs
-77
7-day runs
-69
30-day runs

More Information About wav2vec2-xls-r-sl-a2 huggingface.co Model

More wav2vec2-xls-r-sl-a2 license Visit here:

https://choosealicense.com/licenses/apache-2.0

wav2vec2-xls-r-sl-a2 huggingface.co

wav2vec2-xls-r-sl-a2 huggingface.co is an AI model on huggingface.co that provides wav2vec2-xls-r-sl-a2's model effect (), which can be used instantly with this DrishtiSharma wav2vec2-xls-r-sl-a2 model. huggingface.co supports a free trial of the wav2vec2-xls-r-sl-a2 model, and also provides paid use of the wav2vec2-xls-r-sl-a2. Support call wav2vec2-xls-r-sl-a2 model through api, including Node.js, Python, http.

DrishtiSharma wav2vec2-xls-r-sl-a2 online free

wav2vec2-xls-r-sl-a2 huggingface.co is an online trial and call api platform, which integrates wav2vec2-xls-r-sl-a2's modeling effects, including api services, and provides a free online trial of wav2vec2-xls-r-sl-a2, you can try wav2vec2-xls-r-sl-a2 online for free by clicking the link below.

DrishtiSharma wav2vec2-xls-r-sl-a2 online free url in huggingface.co:

https://huggingface.co/DrishtiSharma/wav2vec2-xls-r-sl-a2

wav2vec2-xls-r-sl-a2 install

wav2vec2-xls-r-sl-a2 is an open source model from GitHub that offers a free installation service, and any user can find wav2vec2-xls-r-sl-a2 on GitHub to install. At the same time, huggingface.co provides the effect of wav2vec2-xls-r-sl-a2 install, users can directly use wav2vec2-xls-r-sl-a2 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

wav2vec2-xls-r-sl-a2 install url in huggingface.co:

https://huggingface.co/DrishtiSharma/wav2vec2-xls-r-sl-a2

Url of wav2vec2-xls-r-sl-a2

wav2vec2-xls-r-sl-a2 huggingface.co Url

Provider of wav2vec2-xls-r-sl-a2 huggingface.co

DrishtiSharma
ORGANIZATIONS

Other API from DrishtiSharma