--- 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](https://huggingface.co/microsoft/speecht5_tts) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4510 ## 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: 0.0001 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 30000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:-----:|:---------------:| | No log | 2.34 | 250 | 0.4040 | | 0.4941 | 4.67 | 500 | 0.3757 | | 0.4941 | 7.01 | 750 | 0.3897 | | 0.4047 | 9.35 | 1000 | 0.3722 | | 0.4047 | 11.68 | 1250 | 0.3740 | | 0.3766 | 14.02 | 1500 | 0.3743 | | 0.3766 | 16.36 | 1750 | 0.3888 | | 0.3689 | 18.69 | 2000 | 0.3749 | | 0.3689 | 21.03 | 2250 | 0.3867 | | 0.349 | 23.36 | 2500 | 0.3795 | | 0.349 | 25.7 | 2750 | 0.3936 | | 0.3424 | 28.04 | 3000 | 0.3786 | | 0.3424 | 30.37 | 3250 | 0.3725 | | 0.3394 | 32.71 | 3500 | 0.3869 | | 0.3394 | 35.05 | 3750 | 0.3978 | | 0.3333 | 37.38 | 4000 | 0.3944 | | 0.3333 | 39.72 | 4250 | 0.4143 | | 0.3293 | 42.06 | 4500 | 0.3949 | | 0.3293 | 44.39 | 4750 | 0.3739 | | 0.3275 | 46.73 | 5000 | 0.3886 | | 0.3275 | 49.07 | 5250 | 0.3900 | | 0.3219 | 51.4 | 5500 | 0.3955 | | 0.3219 | 53.74 | 5750 | 0.4065 | | 0.3147 | 56.07 | 6000 | 0.4022 | | 0.3147 | 58.41 | 6250 | 0.3874 | | 0.3153 | 60.75 | 6500 | 0.3999 | | 0.3153 | 63.08 | 6750 | 0.3880 | | 0.3084 | 65.42 | 7000 | 0.3874 | | 0.3084 | 67.76 | 7250 | 0.4324 | | 0.3067 | 70.09 | 7500 | 0.4177 | | 0.3067 | 72.43 | 7750 | 0.4054 | | 0.3044 | 74.77 | 8000 | 0.4039 | | 0.3044 | 77.1 | 8250 | 0.4080 | | 0.3001 | 79.44 | 8500 | 0.3963 | | 0.3001 | 81.78 | 8750 | 0.4182 | | 0.2965 | 84.11 | 9000 | 0.4026 | | 0.2965 | 86.45 | 9250 | 0.4261 | | 0.2939 | 88.79 | 9500 | 0.4102 | | 0.2939 | 91.12 | 9750 | 0.4187 | | 0.2903 | 93.46 | 10000 | 0.4052 | | 0.2903 | 95.79 | 10250 | 0.4185 | | 0.2904 | 98.13 | 10500 | 0.4092 | | 0.2904 | 100.47 | 10750 | 0.4182 | | 0.285 | 102.8 | 11000 | 0.4127 | | 0.285 | 105.14 | 11250 | 0.4231 | | 0.2859 | 107.48 | 11500 | 0.4053 | | 0.2859 | 109.81 | 11750 | 0.4249 | | 0.2824 | 112.15 | 12000 | 0.4086 | | 0.2824 | 114.49 | 12250 | 0.4232 | | 0.2794 | 116.82 | 12500 | 0.4210 | | 0.2794 | 119.16 | 12750 | 0.4295 | | 0.2803 | 121.5 | 13000 | 0.4412 | | 0.2803 | 123.83 | 13250 | 0.4201 | | 0.277 | 126.17 | 13500 | 0.4181 | | 0.277 | 128.5 | 13750 | 0.4179 | | 0.2744 | 130.84 | 14000 | 0.4257 | | 0.2744 | 133.18 | 14250 | 0.4396 | | 0.2744 | 135.51 | 14500 | 0.4265 | | 0.2744 | 137.85 | 14750 | 0.4198 | | 0.2702 | 140.19 | 15000 | 0.4414 | | 0.2702 | 142.52 | 15250 | 0.4304 | | 0.2661 | 144.86 | 15500 | 0.4444 | | 0.2661 | 147.2 | 15750 | 0.4228 | | 0.2649 | 149.53 | 16000 | 0.4412 | | 0.2649 | 151.87 | 16250 | 0.4269 | | 0.264 | 154.21 | 16500 | 0.4343 | | 0.264 | 156.54 | 16750 | 0.4240 | | 0.2616 | 158.88 | 17000 | 0.4350 | | 0.2616 | 161.21 | 17250 | 0.4430 | | 0.2611 | 163.55 | 17500 | 0.4545 | | 0.2611 | 165.89 | 17750 | 0.4512 | | 0.2601 | 168.22 | 18000 | 0.4569 | | 0.2601 | 170.56 | 18250 | 0.4263 | | 0.2596 | 172.9 | 18500 | 0.4336 | | 0.2596 | 175.23 | 18750 | 0.4464 | | 0.2564 | 177.57 | 19000 | 0.4546 | | 0.2564 | 179.91 | 19250 | 0.4513 | | 0.2554 | 182.24 | 19500 | 0.4349 | | 0.2554 | 184.58 | 19750 | 0.4360 | | 0.255 | 186.92 | 20000 | 0.4571 | | 0.255 | 189.25 | 20250 | 0.4411 | | 0.2525 | 191.59 | 20500 | 0.4435 | | 0.2525 | 193.93 | 20750 | 0.4325 | | 0.251 | 196.26 | 21000 | 0.4441 | | 0.251 | 198.6 | 21250 | 0.4331 | | 0.2505 | 200.93 | 21500 | 0.4484 | | 0.2505 | 203.27 | 21750 | 0.4418 | | 0.2517 | 205.61 | 22000 | 0.4473 | | 0.2517 | 207.94 | 22250 | 0.4519 | | 0.2477 | 210.28 | 22500 | 0.4428 | | 0.2477 | 212.62 | 22750 | 0.4464 | | 0.2468 | 214.95 | 23000 | 0.4387 | | 0.2468 | 217.29 | 23250 | 0.4600 | | 0.2467 | 219.63 | 23500 | 0.4404 | | 0.2467 | 221.96 | 23750 | 0.4586 | | 0.2469 | 224.3 | 24000 | 0.4449 | | 0.2469 | 226.64 | 24250 | 0.4521 | | 0.2445 | 228.97 | 24500 | 0.4480 | | 0.2445 | 231.31 | 24750 | 0.4586 | | 0.2438 | 233.64 | 25000 | 0.4529 | | 0.2438 | 235.98 | 25250 | 0.4515 | | 0.2413 | 238.32 | 25500 | 0.4570 | | 0.2413 | 240.65 | 25750 | 0.4486 | | 0.2449 | 242.99 | 26000 | 0.4490 | | 0.2449 | 245.33 | 26250 | 0.4479 | | 0.2412 | 247.66 | 26500 | 0.4509 | | 0.2412 | 250.0 | 26750 | 0.4472 | | 0.2417 | 252.34 | 27000 | 0.4444 | | 0.2417 | 254.67 | 27250 | 0.4477 | | 0.2407 | 257.01 | 27500 | 0.4494 | | 0.2407 | 259.35 | 27750 | 0.4530 | | 0.2397 | 261.68 | 28000 | 0.4474 | | 0.2397 | 264.02 | 28250 | 0.4484 | | 0.2397 | 266.36 | 28500 | 0.4512 | | 0.2397 | 268.69 | 28750 | 0.4523 | | 0.2397 | 271.03 | 29000 | 0.4451 | | 0.2397 | 273.36 | 29250 | 0.4476 | | 0.241 | 275.7 | 29500 | 0.4515 | | 0.241 | 278.04 | 29750 | 0.4514 | | 0.2395 | 280.37 | 30000 | 0.4510 | ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.0+cu121 - Datasets 2.15.0 - Tokenizers 0.14.1