try_learn_russian_t5

This model is a fine-tuned version of microsoft/speecht5_tts on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5077

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5782	6.64	1000	0.5444
0.5452	13.29	2000	0.5202
0.5403	19.93	3000	0.5139
0.5342	26.58	4000	0.5077

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0