aconeil / w2v2-lmk_updated

huggingface.co
Total runs: 16
24-hour runs: 0
7-day runs: -173
30-day runs: -167
Model's Last Updated: November 22 2025
automatic-speech-recognition

Introduction of w2v2-lmk_updated

Model Details of w2v2-lmk_updated

w2v2-lmk_updated

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the audiofolder dataset. It achieves the following results on the evaluation set:

  • Loss: 2.2629
  • Wer: 0.7700
  • Cer: 0.3244
Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure
Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 300
  • num_epochs: 100
  • mixed_precision_training: Native AMP
Training results
Training Loss Epoch Step Validation Loss Wer Cer
5.732 6.25 100 3.3371 1.0 1.0
3.0052 12.5 200 2.8812 1.0 1.0
2.6434 18.75 300 2.3653 1.0 0.8850
0.8393 25.0 400 1.5602 0.7770 0.3488
0.2892 31.25 500 1.6106 0.7770 0.3298
0.1167 37.5 600 1.7649 0.7909 0.3267
0.0595 43.75 700 1.8324 0.7666 0.3138
0.0337 50.0 800 2.0307 0.7875 0.3351
0.0222 56.25 900 2.0604 0.7840 0.3305
0.015 62.5 1000 2.1389 0.7735 0.3313
0.0127 68.75 1100 2.1756 0.7700 0.3260
0.0109 75.0 1200 2.2084 0.7805 0.3283
0.0097 81.25 1300 2.2374 0.7805 0.3267
0.0088 87.5 1400 2.2508 0.7700 0.3252
0.008 93.75 1500 2.2586 0.7735 0.3252
0.0077 100.0 1600 2.2629 0.7700 0.3244
Framework versions
  • Transformers 4.57.1
  • Pytorch 2.8.0+cu128
  • Datasets 3.0.0
  • Tokenizers 0.22.1

Runs of aconeil w2v2-lmk_updated on huggingface.co

16
Total runs
0
24-hour runs
1
3-day runs
-173
7-day runs
-167
30-day runs

More Information About w2v2-lmk_updated huggingface.co Model

More w2v2-lmk_updated license Visit here:

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

w2v2-lmk_updated huggingface.co

w2v2-lmk_updated huggingface.co is an AI model on huggingface.co that provides w2v2-lmk_updated's model effect (), which can be used instantly with this aconeil w2v2-lmk_updated model. huggingface.co supports a free trial of the w2v2-lmk_updated model, and also provides paid use of the w2v2-lmk_updated. Support call w2v2-lmk_updated model through api, including Node.js, Python, http.

w2v2-lmk_updated huggingface.co Url

https://huggingface.co/aconeil/w2v2-lmk_updated

aconeil w2v2-lmk_updated online free

w2v2-lmk_updated huggingface.co is an online trial and call api platform, which integrates w2v2-lmk_updated's modeling effects, including api services, and provides a free online trial of w2v2-lmk_updated, you can try w2v2-lmk_updated online for free by clicking the link below.

aconeil w2v2-lmk_updated online free url in huggingface.co:

https://huggingface.co/aconeil/w2v2-lmk_updated

w2v2-lmk_updated install

w2v2-lmk_updated is an open source model from GitHub that offers a free installation service, and any user can find w2v2-lmk_updated on GitHub to install. At the same time, huggingface.co provides the effect of w2v2-lmk_updated install, users can directly use w2v2-lmk_updated installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

w2v2-lmk_updated install url in huggingface.co:

https://huggingface.co/aconeil/w2v2-lmk_updated

Url of w2v2-lmk_updated

w2v2-lmk_updated huggingface.co Url

Provider of w2v2-lmk_updated huggingface.co

aconeil
ORGANIZATIONS

Other API from aconeil

huggingface.co

Total runs: 11
Run Growth: 7
Growth Rate: 63.64%
Updated:February 16 2026
huggingface.co

Total runs: 10
Run Growth: 6
Growth Rate: 60.00%
Updated:April 04 2026
huggingface.co

Total runs: 2
Run Growth: 0
Growth Rate: 0.00%
Updated:November 30 2024