w2v-bert-2.0-khmer / README.md
seanghay's picture
Upload Wav2Vec2BertForCTC
1f6e156 verified
|
raw
history blame
1.13 kB
metadata
base_model: facebook/w2v-bert-2.0
datasets:
  - openslr
language:
  - km
license: mit
tags:
  - automatic-speech-recognition
  - openslr
  - generated_from_trainer
model-index:
  - name: training
    results: []

training

This model is a fine-tuned version of facebook/w2v-bert-2.0 on the openslr dataset.

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: 1e-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 15

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.0.1
  • Datasets 2.20.0
  • Tokenizers 0.19.1