Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
ssc-ush-mms-model-mix-adapt-max-longcv – AI Model by ctaguchi | AlphaNeural AI | AlphaNeural AI
You can deploy this model and start earning money today!
ctaguchi
/
ssc-ush-mms-model-mix-adapt-max-longcv
like
0
transformers
safetensors
wav2vec2
automatic-speech-recognition
generated_from_trainer
facebook/mms-1b-all
finetune
cc-by-nc-4.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
ssc-ush-mms-model-mix-adapt-max-longcv
This model is a fine-tuned version of
facebook/mms-1b-all
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.4095
Cer: 0.1221
Wer: 0.4335
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: 0.001
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH 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: 15
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Cer
Wer
4.0319
3.125
200
3.2006
0.9733
1.0
0.5929
6.25
400
0.4704
0.1349
0.5062
0.4709
9.375
600
0.4133
0.1243
0.4387
0.4233
12.5
800
0.4095
0.1221
0.4335
Framework versions
Transformers 4.52.1
Pytorch 2.9.1+cu128
Datasets 3.6.0
Tokenizers 0.21.4
