last_vc

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

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-06
train_batch_size: 8
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 64
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
training_steps: 4000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.7194	0.3820	100	0.6257
0.6475	0.7641	200	0.5903
0.622	1.1452	300	0.5744
0.6042	1.5272	400	0.5645
0.5932	1.9093	500	0.5568
0.5962	2.2904	600	0.5545
0.5877	2.6724	700	0.5494
0.572	3.0535	800	0.5465
0.5705	3.4355	900	0.5434
0.5698	3.8176	1000	0.5394
0.5661	4.1987	1100	0.5393
0.5569	4.5807	1200	0.5378
0.5627	4.9628	1300	0.5363
0.5596	5.3438	1400	0.5338
0.5581	5.7259	1500	0.5310
0.5542	6.1070	1600	0.5307
0.5483	6.4890	1700	0.5304
0.5536	6.8711	1800	0.5273
0.5595	7.2521	1900	0.5273
0.5448	7.6342	2000	0.5276
0.5429	8.0153	2100	0.5270
0.5507	8.3973	2200	0.5261
0.5511	8.7794	2300	0.5251
0.5501	9.1605	2400	0.5243
0.5434	9.5425	2500	0.5254
0.5434	9.9245	2600	0.5249
0.5477	10.3056	2700	0.5210
0.5455	10.6877	2800	0.5213
0.5412	11.0688	2900	0.5212
0.5416	11.4508	3000	0.5203
0.5417	11.8329	3100	0.5236
0.5361	12.2139	3200	0.5220
0.5411	12.5960	3300	0.5220
0.5446	12.9780	3400	0.5191
0.5415	13.3591	3500	0.5199
0.5426	13.7412	3600	0.5210
0.5391	14.1223	3700	0.5198
0.5418	14.5043	3800	0.5196
0.5437	14.8863	3900	0.5195
0.539	15.2674	4000	0.5195