Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-ckm-7 – AI Model by ninninz | AlphaNeural AI
You can deploy this model and start earning money today!
ninninz
/
whisper-ckm-7
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
generated_from_trainer
audiofolder
openai/whisper-large-v3
finetune
apache-2.0
model-index
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper-large-v3-croarian_overlap_removed_10
This model is a fine-tuned version of
openai/whisper-large-v3
on the audiofolder dataset. It achieves the following results on the evaluation set:
Loss: 2.2772
Wer: 76.4906
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: 16
eval_batch_size: 8
seed: 42
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
0.0473
12.66
1000
1.8439
71.3458
0.0101
25.32
2000
2.0913
66.2919
0.007
37.97
3000
2.2344
74.4009
0.0055
50.63
4000
2.2772
76.4906
Framework versions
Transformers 4.37.1
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.1
