Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-large-khmer-asr – AI Model by ksoky | AlphaNeural AI
You can deploy this model and start earning money today!
ksoky
/
whisper-large-khmer-asr
like
0
transformers
pytorch
tensorboard
whisper
automatic-speech-recognition
hf-asr-leaderboard
generated_from_trainer
km
openslr
apache-2.0
model-index
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Whisper Large Khmer - Kak Soky
This model is a fine-tuned version of
openai/whisper-large
on the SLR42 dataset. It achieves the following results on the evaluation set:
Loss: 0.2375
Wer: 29.5183
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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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
0.0102
12.34
1000
0.2228
38.2659
0.0003
24.69
2000
0.2260
30.7900
0.0001
37.04
3000
0.2310
30.0578
0.0
49.38
4000
0.2375
29.5183
Framework versions
Transformers 4.25.0.dev0
Pytorch 1.9.1+cu111
Datasets 2.3.2
Tokenizers 0.12.1
