zlm_b64_le3_s4000 – AI Model by mikhail-panzo | AlphaNeural AI

You can deploy this model and start earning money today!

mikhail-panzo/
zlm_b64_le3_s4000

like

0

generated_from_trainer

microsoft/speecht5_tts

endpoints_compatible

Views

No views yet

zlm_b64

This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.7960

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: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2000
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4734	0.4188	500	0.4319
0.4686	0.8377	1000	0.4433
2.9342	1.2565	1500	2.8256
2.8065	1.6754	2000	2.7988
2.8176	2.0942	2500	2.8305
2.7931	2.5131	3000	2.7955
2.8172	2.9319	3500	2.8076
2.802	3.3508	4000	2.7960

Framework versions

Transformers 4.41.0.dev0
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1