Hugging Face's logo

zainulhakim
/
240624-wav2vec2-ASR-Arab

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
240624-wav2vec2-ASR-Arab / README.md
zainulhakim's picture
zainulhakim
Upload processor
8cf859c verified
preview code
|
raw
history blame
1.61 kB
metadata
base_model: zainulhakim/240615-wav2vec2-ASR-Arabs
license: apache-2.0
metrics:
  - wer
tags:
  - generated_from_trainer
model-index:
  - name: 240624-wav2vec2-ASR-Arab
    results: []

240624-wav2vec2-ASR-Arab

This model is a fine-tuned version of zainulhakim/240615-wav2vec2-ASR-Arabs on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4394
  • Wer: 0.9293

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: 0.0001
  • train_batch_size: 5
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
No log 6.25 100 2.5463 1.0
No log 12.5 200 1.4375 1.0
No log 18.75 300 1.4394 0.9293

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.1+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1