You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

whisper-tiny-khmer-aug-v7

This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_steps: 1000
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Wer
0.9369	1.0	984	0.5447	101.5478
0.3966	2.0	1968	0.4189	101.9624
0.3014	3.0	2952	0.3597	101.9624
0.254	4.0	3936	0.3278	123.8253
0.2238	5.0	4920	0.3181	103.9801
0.2041	6.0	5904	0.3107	107.9326
0.188	7.0	6888	0.3138	107.1587
0.1728	8.0	7872	0.3164	101.5755
0.1611	9.0	8856	0.3153	99.7512
0.1515	10.0	9840	0.3184	105.9978

Safetensors

Model size

37.8M params

Tensor type

F32

Base model

Finetuned

this model