TTS_FineTune_French

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: 0.5870

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Use 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
• training_steps: 600
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.0764	100.0	100	0.4995
0.8705	200.0	200	0.5197
0.7866	300.0	300	0.5469
0.7062	400.0	400	0.5615
0.671	500.0	500	0.5805
0.6184	600.0	600	0.5870

Framework versions

• Transformers 4.47.0.dev0
• Pytorch 2.5.0+cu121
• Datasets 3.0.2
• Tokenizers 0.20.1