Hugging Face's logo

octava
/
optimized-sm-whisper-id

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Indonesian
whisper
Generated from Trainer
Model card Files Metrics Community
optimized-sm-whisper-id / README.md
octava's picture
octava
Training in progress, step 1000
269f2ac verified
preview code
|
raw
history blame contribute delete
1.63 kB
metadata
library_name: transformers
language:
  - id
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - octava/indonesian-voice-transcription-1.4.9a-cv-fl-slrjv-md
model-index:
  - name: Optimized Whisper Small Id for Inspirasi
    results: []

Optimized Whisper Small Id for Inspirasi

This model is a fine-tuned version of openai/whisper-small on the Extracted Youtube with CommonVoice11, Fleurs, OpenSLR, and MagicData dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.3722
  • eval_wer: 20.3324
  • eval_runtime: 495.0068
  • eval_samples_per_second: 3.527
  • eval_steps_per_second: 0.222
  • epoch: 3.0354
  • step: 9000

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: 32
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 10000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.49.0
  • Pytorch 2.2.0a0+81ea7a4
  • Datasets 3.3.2
  • Tokenizers 0.21.0