Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
wav2vec2-base-960h-finetuned-ks – AI Model by faizandigi009 | AlphaNeural AI
You can deploy this model and start earning money today!
faizandigi009
/
wav2vec2-base-960h-finetuned-ks
like
0
transformers
safetensors
wav2vec2
audio-classification
generated_from_trainer
audiofolder
facebook/wav2vec2-base-960h
finetune
model-index
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
wav2vec2-base-960h-finetuned-ks
This model is a fine-tuned version of
facebook/wav2vec2-base-960h
on the audiofolder dataset. It achieves the following results on the evaluation set:
Loss: 0.2908
Accuracy: 0.8929
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: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 4
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
0.5519
1.0
70
0.4880
0.8571
0.8835
2.0
140
0.6964
0.7286
0.3766
3.0
210
0.3114
0.8714
0.2251
4.0
280
0.2908
0.8929
Framework versions
Transformers 4.51.3
Pytorch 2.7.0+cpu
Datasets 3.5.1
Tokenizers 0.21.1
