Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-smol-tr-0904 – AI Model by C10X | AlphaNeural AI
You can deploy this model and start earning money today!
C10X
/
whisper-smol-tr-0904
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
generated_from_trainer
openai/whisper-large-v3-turbo
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper-smol-tr-0904
This model is a fine-tuned version of
openai/whisper-large-v3-turbo
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 1.4512
Wer: 16.3148
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: 4
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 64
optimizer: Use adamw_bnb_8bit 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: 100
num_epochs: 3.0
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
No log
1.0
5
1.8572
15.5470
No log
2.0
10
1.6003
16.1228
No log
2.4776
12
1.4512
16.3148
Framework versions
Transformers 4.51.1
Pytorch 2.5.1+cu121
Datasets 3.5.0
Tokenizers 0.21.0
