metadata

license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
model-index:
  - name: speecht5_tts
    results: []

speecht5_tts

This model is a fine-tuned version of microsoft/speecht5_tts on the None 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:

Training Loss	Epoch	Step	Validation Loss
No log	0.53	250	1.1630
1.3203	1.06	500	0.8518
1.3203	1.6	750	0.7785
0.8972	2.13	1000	0.7502
0.8972	2.66	1250	0.7369
0.8135	3.19	1500	0.7193
0.8135	3.72	1750	0.7152
0.777	4.26	2000	0.7082
0.777	4.79	2250	0.7076
0.7586	5.32	2500	0.6965
0.7586	5.85	2750	0.6894
0.747	6.38	3000	0.6790
0.747	6.91	3250	0.6858
0.7315	7.45	3500	0.6906
0.7315	7.98	3750	0.6687
0.7153	8.51	4000	0.6731
0.7153	9.04	4250	0.6732
0.7119	9.57	4500	0.6706
0.7119	10.11	4750	0.6648
0.6952	10.64	5000	0.6638
0.6952	11.17	5250	0.6652
0.6904	11.7	5500	0.6667
0.6904	12.23	5750	0.6629
0.6774	12.77	6000	0.6614
0.6774	13.3	6250	0.6644
0.6812	13.83	6500	0.6638
0.6812	14.36	6750	0.6621
0.6644	14.89	7000	0.6621
0.6644	15.43	7250	0.6604
0.6615	15.96	7500	0.6690
0.6615	16.49	7750	0.6540
0.6636	17.02	8000	0.6613
0.6636	17.55	8250	0.6637
0.6523	18.09	8500	0.6687
0.6523	18.62	8750	0.6582
0.6462	19.15	9000	0.6597
0.6462	19.68	9250	0.6586
0.6437	20.21	9500	0.6614
0.6437	20.74	9750	0.6627
0.6418	21.28	10000	0.6641
0.6418	21.81	10250	0.6633
0.6416	22.34	10500	0.6636
0.6416	22.87	10750	0.6623
0.6341	23.4	11000	0.6609
0.6341	23.94	11250	0.6615
0.6328	24.47	11500	0.6656
0.6328	25.0	11750	0.6609
0.6277	25.53	12000	0.6672
0.6277	26.06	12250	0.6636
0.6216	26.6	12500	0.6603
0.6216	27.13	12750	0.6673
0.6311	27.66	13000	0.6700
0.6311	28.19	13250	0.6616
0.6211	28.72	13500	0.6638
0.6211	29.26	13750	0.6610
0.6192	29.79	14000	0.6670
0.6192	30.32	14250	0.6679
0.6205	30.85	14500	0.6703
0.6205	31.38	14750	0.6636
0.6161	31.91	15000	0.6650