speecht5_finetuned_voxpopuli_de_Merkel

This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4112

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: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• 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: 10000

Training results

Training Loss	Epoch	Step	Validation Loss
0.4831	4.06	1000	0.4406
0.4583	8.12	2000	0.4271
0.4482	12.18	3000	0.4177
0.4435	16.24	4000	0.4148
0.433	20.3	5000	0.4142
0.4333	24.37	6000	0.4128
0.4306	28.43	7000	0.4111
0.4288	32.49	8000	0.4110
0.4262	36.55	9000	0.4109
0.4228	40.61	10000	0.4112

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.0
• Tokenizers 0.13.3