Hugging Face's logo

legendary2910
/
Mnong-ASR-v1

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Vietnamese
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Mnong-ASR-v1 / README.md
legendary2910's picture
legendary2910
Upload tokenizer
41b6e55 verified
preview code
|
raw
history blame
No virus
1.67 kB
metadata
base_model: openai/whisper-medium
language:
  - vi
license: apache-2.0
metrics:
  - wer
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Medium Mnong
    results: []

Whisper Medium Mnong

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

  • Loss: 0.2759
  • Wer: 20.7811

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
0.3667 2.0325 1000 0.5079 42.3819
0.0556 4.0650 2000 0.3091 24.1080
0.0089 6.0976 3000 0.2708 17.7917
0.0012 8.1301 4000 0.2759 20.7811

Framework versions

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