Hugging Face's logo

PhanithLIM
/
xwhisper-kh-base

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xwhisper-kh-base / README.md
PhanithLIM's picture
PhanithLIM
Upload checkpoint
33881df verified
preview code
|
raw
history blame contribute delete
1.81 kB
metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: xwhisper-kh-base
    results: []

xwhisper-kh-base

This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2711
  • Wer: 74.0769

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: constant
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.8338 1.0 1087 0.4122 90.5307
0.3136 2.0 2174 0.3022 80.1699
0.2199 3.0 3261 0.2599 76.6601
0.1675 4.0 4348 0.2483 74.3577
0.1294 5.0 5435 0.2483 72.6309
0.1001 6.0 6522 0.2555 74.8982
0.0759 7.0 7609 0.2711 74.0769

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.4.0
  • Datasets 3.1.0
  • Tokenizers 0.20.3