mms_knn_vc – AI Model by resproj007 | AlphaNeural AI

You can deploy this model and start earning money today!

resproj007/
mms_knn_vc

like

0

automatic-speech-recognition

generated_from_trainer

facebook/mms-1b-all

endpoints_compatible

Views

No views yet

mms_knn_vc

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: 1.6851
Wer: 0.5400
Cer: 0.3424
Bertscore Precision: 0.6802
Bertscore Recall: 0.7134
Bertscore F1: 0.6932

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: 4
total_train_batch_size: 32
optimizer: Use 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: 50
training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer	Bertscore Precision	Bertscore Recall	Bertscore F1
1.3967	19.0125	500	1.5072	0.5607	0.3355	0.6606	0.6987	0.6757
1.1303	39.0125	1000	1.5313	0.5439	0.3280	0.6681	0.7061	0.6832
0.897	59.0125	1500	1.6450	0.5506	0.3428	0.6727	0.7083	0.6867
0.8015	79.0125	2000	1.6851	0.5400	0.3424	0.6802	0.7134	0.6932

Framework versions

Transformers 4.57.6
Pytorch 2.8.0+cu128
Datasets 4.5.0
Tokenizers 0.22.2