Hugging Face's logo

legendary2910
/
Mnong-ASR-v3

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Vietnamese
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Mnong-ASR-v3 / README.md
legendary2910's picture
legendary2910
Upload tokenizer
d4c6cbd verified
preview code
|
raw
history blame
1.67 kB
metadata
base_model: openai/whisper-base
language:
  - vi
license: apache-2.0
metrics:
  - wer
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Base Mnong
    results: []

Whisper Base Mnong

This model is a fine-tuned version of openai/whisper-base on the MnongAudio-v2 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7309
  • Wer: 78.4474

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: 8
  • 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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
1.2709 2.0325 1000 1.3573 121.7936
0.5929 4.0650 2000 0.9105 81.5333
0.2907 6.0976 3000 0.7671 80.9065
0.204 8.1301 4000 0.7309 78.4474

Framework versions

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