jaeyeon / wav2vec2-child-en-tokenizer-4

huggingface.co
Total runs: 3.5K
24-hour runs: 45
7-day runs: 52
30-day runs: -154
Model's Last Updated: April 10 2022
automatic-speech-recognition

Introduction of wav2vec2-child-en-tokenizer-4

Model Details of wav2vec2-child-en-tokenizer-4

wav2vec2-child-en-tokenizer-4

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4709
  • Wer: 0.3769
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: 0.0003
  • train_batch_size: 24
  • eval_batch_size: 24
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 48
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 30
  • mixed_precision_training: Native AMP
Training results
Training Loss Epoch Step Validation Loss Wer
0.0334 1.72 100 1.4709 0.3769
0.0332 3.45 200 1.4709 0.3769
0.0343 5.17 300 1.4709 0.3769
0.032 6.9 400 1.4709 0.3769
0.0332 8.62 500 1.4709 0.3769
0.0327 10.34 600 1.4709 0.3769
0.0331 12.07 700 1.4709 0.3769
0.0334 13.79 800 1.4709 0.3769
0.0319 15.52 900 1.4709 0.3769
0.0338 17.24 1000 1.4709 0.3769
0.0321 18.97 1100 1.4709 0.3769
0.0367 20.69 1200 1.4709 0.3769
0.0331 22.41 1300 1.4709 0.3769
0.0332 24.14 1400 1.4709 0.3769
0.0347 25.86 1500 1.4709 0.3769
0.0319 27.59 1600 1.4709 0.3769
0.0302 29.31 1700 1.4709 0.3769
Framework versions
  • Transformers 4.11.3
  • Pytorch 1.10.0+cu113
  • Datasets 1.18.3
  • Tokenizers 0.10.3

Runs of jaeyeon wav2vec2-child-en-tokenizer-4 on huggingface.co

3.5K
Total runs
45
24-hour runs
224
3-day runs
52
7-day runs
-154
30-day runs

More Information About wav2vec2-child-en-tokenizer-4 huggingface.co Model

More wav2vec2-child-en-tokenizer-4 license Visit here:

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

wav2vec2-child-en-tokenizer-4 huggingface.co

wav2vec2-child-en-tokenizer-4 huggingface.co is an AI model on huggingface.co that provides wav2vec2-child-en-tokenizer-4's model effect (), which can be used instantly with this jaeyeon wav2vec2-child-en-tokenizer-4 model. huggingface.co supports a free trial of the wav2vec2-child-en-tokenizer-4 model, and also provides paid use of the wav2vec2-child-en-tokenizer-4. Support call wav2vec2-child-en-tokenizer-4 model through api, including Node.js, Python, http.

wav2vec2-child-en-tokenizer-4 huggingface.co Url

https://huggingface.co/jaeyeon/wav2vec2-child-en-tokenizer-4

jaeyeon wav2vec2-child-en-tokenizer-4 online free

wav2vec2-child-en-tokenizer-4 huggingface.co is an online trial and call api platform, which integrates wav2vec2-child-en-tokenizer-4's modeling effects, including api services, and provides a free online trial of wav2vec2-child-en-tokenizer-4, you can try wav2vec2-child-en-tokenizer-4 online for free by clicking the link below.

jaeyeon wav2vec2-child-en-tokenizer-4 online free url in huggingface.co:

https://huggingface.co/jaeyeon/wav2vec2-child-en-tokenizer-4

wav2vec2-child-en-tokenizer-4 install

wav2vec2-child-en-tokenizer-4 is an open source model from GitHub that offers a free installation service, and any user can find wav2vec2-child-en-tokenizer-4 on GitHub to install. At the same time, huggingface.co provides the effect of wav2vec2-child-en-tokenizer-4 install, users can directly use wav2vec2-child-en-tokenizer-4 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

wav2vec2-child-en-tokenizer-4 install url in huggingface.co:

https://huggingface.co/jaeyeon/wav2vec2-child-en-tokenizer-4

Url of wav2vec2-child-en-tokenizer-4

wav2vec2-child-en-tokenizer-4 huggingface.co Url

Provider of wav2vec2-child-en-tokenizer-4 huggingface.co

jaeyeon
ORGANIZATIONS

Other API from jaeyeon