enko_xlsr_13p_run1 / README.md
yesj1234's picture
Upload folder using huggingface_hub
99d6d7b
|
raw
history blame
2.18 kB
metadata
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - automatic-speech-recognition
  - ./sample_speech.py
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: enko_xlsr_13p_run1
    results: []

enko_xlsr_13p_run1

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

  • Loss: 0.3042
  • Wer: 0.1696

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: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • total_eval_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Wer
0.6595 1.0 7702 0.4495 0.2974
0.5717 2.0 15404 0.3982 0.2562
0.5134 3.0 23106 0.3769 0.2365
0.467 4.0 30808 0.3499 0.2203
0.4156 5.0 38510 0.3391 0.2116
0.379 6.0 46212 0.3327 0.1999
0.3475 7.0 53914 0.3127 0.1947
0.3105 8.0 61616 0.3081 0.1814
0.281 9.0 69318 0.3068 0.1742
0.2584 10.0 77020 0.3040 0.1713

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.14.1