Hugging Face's logo

ashe194
/
wav2vec2-xlsr-ft-combined_5gram

Safetensors
wav2vec2
Generated from Trainer
Model card Files Community
wav2vec2-xlsr-ft-combined_5gram / README.md
ashe194's picture
ashe194
initial commit of existing fine tuned model
d6502e3
preview code
|
raw
history blame contribute delete
1.95 kB
metadata
license: apache-2.0
base_model: jonatasgrosman/wav2vec2-large-xlsr-53-english
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: wav2vec2-xlsr-fine-tuning
    results: []

Visualize in Weights & Biases

wav2vec2-xlsr-fine-tuning

This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-english on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0241
  • Wer: 3.3688

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: 4e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
No log 0.9935 76 0.0404 4.7163
No log 2.0 153 0.0292 3.8179
No log 2.9935 229 0.0247 3.4436
No log 3.9739 304 0.0241 3.3688

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1