Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
whisper_large_v2_thi_dataset-with-timestamps – AI Model by PThi35 | AlphaNeural AI
You can deploy this model and start earning money today!
PThi35
/
whisper_large_v2_thi_dataset-with-timestamps
like
0
safetensors
whisper
generated_from_trainer
openai/whisper-large-v2
finetune
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper_large_v2_thi_dataset-with-timestamps
This model is a fine-tuned version of
openai/whisper-large-v2
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.4791
Cer: 14.7599
Wer: 25.2521
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: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
num_epochs: 3
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Cer
Wer
0.8271
0.9998
3132
0.5218
16.4970
28.6456
0.4996
2.0
6265
0.4891
17.2551
29.3134
0.4217
2.9995
9396
0.4791
14.7599
25.2521
Framework versions
Transformers 4.41.2
Pytorch 2.1.2+cu118
Datasets 2.19.0
Tokenizers 0.19.1
