Hugging Face's logo

zainulhakim
/
240624-wav2vec2-ASR-Arab

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
Edit model card

Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases

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: 1.6706
  • Wer: 0.9697

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 2.5459 1.0
No log 12.5 200 1.4102 1.0
No log 18.75 300 1.6706 0.9697

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1
Downloads last month
4
Safetensors
Model size
94.4M params
Tensor type
F32
·
Inference Examples
Automatic Speech Recognition
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for zainulhakim/240624-wav2vec2-ASR-Arab

Finetunes
3 models

Evaluation results

Metadata error: specify a dataset to view leaderboard