Hugging Face's logo

AshtonLKY
/
Whisper_ASR_ATC_v6

Automatic Speech Recognition
Transformers
Safetensors
English
whisper
asr-fyp
Generated from Trainer
Inference Endpoints
Model card Files Community
Whisper_ASR_ATC_v6 / README.md
AshtonLKY's picture
AshtonLKY
End of training
8628ca6 verified
preview code
|
raw
history blame
1.45 kB
metadata
library_name: transformers
language:
  - en
license: apache-2.0
base_model: openai/whisper-small
tags:
  - asr-fyp
  - generated_from_trainer
datasets:
  - AshtonLKY/Whisper_ASR_ATC
model-index:
  - name: Whisper_ASR_ATC
    results: []

Whisper_ASR_ATC

This model is a fine-tuned version of openai/whisper-small on the AshtonLKY/augmented_audio dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.1539
  • eval_wer: 12.9843
  • eval_runtime: 5304.4418
  • eval_samples_per_second: 2.533
  • eval_steps_per_second: 0.158
  • epoch: 1.1905
  • step: 4000

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: 1e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 25000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1