Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
ssc-el-CY-xlsr300m-model-mix-adapt-max-lowlr – AI Model by ctaguchi | AlphaNeural AI
You can deploy this model and start earning money today!
ctaguchi
/
ssc-el-CY-xlsr300m-model-mix-adapt-max-lowlr
like
0
transformers
safetensors
wav2vec2
automatic-speech-recognition
generated_from_trainer
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
ssc-el-CY-xlsr300m-model-mix-adapt-max-lowlr
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 1.9725
Cer: 0.2493
Wer: 0.6990
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: 0.0003
train_batch_size: 2
eval_batch_size: 6
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 5
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Cer
Wer
1.6201
1.0205
200
1.7307
0.2651
0.7366
1.3829
2.0409
400
1.7478
0.2618
0.7223
0.4969
3.0614
600
1.8160
0.2425
0.6868
0.9479
4.0818
800
1.9725
0.2493
0.6990
Framework versions
Transformers 4.57.2
Pytorch 2.9.1+cu128
Datasets 3.6.0
Tokenizers 0.22.0
