xlsr_mid2_zh-ko / README.md
yesj1234's picture
Upload folder using huggingface_hub
dbd770d
metadata
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - automatic-speech-recognition
  - ./sample_speech.py
  - generated_from_trainer
model-index:
  - name: zh-xlsr3
    results: []

zh-xlsr3

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: 1.9402
  • Cer: 0.4156

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: 4
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss Cer
2.9893 6.08 2000 2.4704 0.5279
1.9656 12.16 4000 1.9401 0.4185
1.4552 18.24 6000 1.9569 0.4053
1.1015 24.32 8000 2.1087 0.3982
0.8761 30.4 10000 2.2972 0.4272
0.6962 36.47 12000 2.4389 0.4153
0.5562 42.55 14000 2.5137 0.4164

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.5
  • Tokenizers 0.14.1