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	2.34	250	0.5148
0.5893	4.67	500	0.3786
0.5893	7.01	750	0.3621
0.4015	9.35	1000	0.3600
0.4015	11.68	1250	0.3701
0.3739	14.02	1500	0.3612
0.3739	16.36	1750	0.3626
0.3634	18.69	2000	0.3499
0.3634	21.03	2250	0.3549
0.3499	23.36	2500	0.3600
0.3499	25.7	2750	0.3533
0.3428	28.04	3000	0.3652
0.3428	30.37	3250	0.3541
0.3407	32.71	3500	0.3579
0.3407	35.05	3750	0.3550
0.3368	37.38	4000	0.3624
0.3368	39.72	4250	0.3621
0.3315	42.06	4500	0.3577
0.3315	44.39	4750	0.3620
0.3305	46.73	5000	0.3665
0.3305	49.07	5250	0.3641
0.3273	51.4	5500	0.3563
0.3273	53.74	5750	0.3579
0.3228	56.07	6000	0.3615
0.3228	58.41	6250	0.3606
0.3227	60.75	6500	0.3647
0.3227	63.08	6750	0.3647
0.3183	65.42	7000	0.3619
0.3183	67.76	7250	0.3786
0.3184	70.09	7500	0.3731
0.3184	72.43	7750	0.3630
0.3177	74.77	8000	0.3647
0.3177	77.1	8250	0.3668
0.3159	79.44	8500	0.3624
0.3159	81.78	8750	0.3742
0.3129	84.11	9000	0.3722
0.3129	86.45	9250	0.3755
0.3124	88.79	9500	0.3693
0.3124	91.12	9750	0.3707
0.3094	93.46	10000	0.3808
0.3094	95.79	10250	0.3696
0.3116	98.13	10500	0.3773
0.3116	100.47	10750	0.3796
0.3076	102.8	11000	0.3705
0.3076	105.14	11250	0.3718
0.3104	107.48	11500	0.3792
0.3104	109.81	11750	0.3714
0.3078	112.15	12000	0.3765
0.3078	114.49	12250	0.3803
0.3064	116.82	12500	0.3792
0.3064	119.16	12750	0.3803
0.3087	121.5	13000	0.3806
0.3087	123.83	13250	0.3821
0.3064	126.17	13500	0.3795
0.3064	128.5	13750	0.3766
0.3066	130.84	14000	0.3780
0.3066	133.18	14250	0.3858
0.3081	135.51	14500	0.3812
0.3081	137.85	14750	0.3829
0.3064	140.19	15000	0.3812