TrorYongASR2-small - test

This model is a fine-tuned version of KrorngAI/TrorYongASR2-small on the Khmer MPWT Speech dataset. It achieves the following results on the evaluation set:

Loss: 0.6424
Wer: 16.1740

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: 2e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 40
training_steps: 400
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0	0	3.7000	47.4066
1.4733	0.8621	100	0.9034	20.2454
1.0191	1.7241	200	0.7100	16.0625
0.8008	2.5862	300	0.6571	16.3971
0.7018	3.4483	400	0.6424	16.1740

Framework versions

Transformers 5.20.1
Pytorch 2.11.0+cu130
Datasets 4.8.5
Tokenizers 0.23.3

Downloads last month: -

Safetensors

Model size

0.1B params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Kimang18/TrorYongASR2-small-km

Base model

KrorngAI/TrorYongASR2-small

Finetuned

(1)

this model

Dataset used to train Kimang18/TrorYongASR2-small-km

Evaluation results

Wer on Khmer MPWT Speech
self-reported

16.174