speecht5_finetuned_voxpopuli_nl

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

• Loss: 0.4816

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: 250
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
0.8188	0.85	50	0.7075
0.7124	1.71	100	0.6201
0.6763	2.56	150	0.5924
0.6367	3.42	200	0.5586
0.576	4.27	250	0.5216
0.5591	5.13	300	0.5097
0.5457	5.98	350	0.5027
0.5447	6.84	400	0.4999
0.5413	7.69	450	0.4933
0.5288	8.55	500	0.4913
0.5231	9.4	550	0.4881
0.5276	10.26	600	0.4874
0.52	11.11	650	0.4848
0.5238	11.97	700	0.4863
0.5163	12.82	750	0.4848
0.5191	13.68	800	0.4838
0.5163	14.53	850	0.4828
0.5126	15.38	900	0.4824
0.5155	16.24	950	0.4836
0.5193	17.09	1000	0.4816

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3