|
--- |
|
license: mit |
|
base_model: microsoft/speecht5_tts |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: speecht5_tts |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# 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: 0.6228 |
|
|
|
## 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 | 3.85 | 250 | 0.5310 | |
|
| 0.6287 | 7.69 | 500 | 0.5088 | |
|
| 0.6287 | 11.54 | 750 | 0.4855 | |
|
| 0.5138 | 15.38 | 1000 | 0.4986 | |
|
| 0.5138 | 19.23 | 1250 | 0.4820 | |
|
| 0.4735 | 23.08 | 1500 | 0.4775 | |
|
| 0.4735 | 26.92 | 1750 | 0.5104 | |
|
| 0.4512 | 30.77 | 2000 | 0.4953 | |
|
| 0.4512 | 34.62 | 2250 | 0.4838 | |
|
| 0.4419 | 38.46 | 2500 | 0.4969 | |
|
| 0.4419 | 42.31 | 2750 | 0.5057 | |
|
| 0.4313 | 46.15 | 3000 | 0.4931 | |
|
| 0.4313 | 50.0 | 3250 | 0.4975 | |
|
| 0.4164 | 53.85 | 3500 | 0.5145 | |
|
| 0.4164 | 57.69 | 3750 | 0.5070 | |
|
| 0.4055 | 61.54 | 4000 | 0.4921 | |
|
| 0.4055 | 65.38 | 4250 | 0.5139 | |
|
| 0.3999 | 69.23 | 4500 | 0.5111 | |
|
| 0.3999 | 73.08 | 4750 | 0.5118 | |
|
| 0.3895 | 76.92 | 5000 | 0.5184 | |
|
| 0.3895 | 80.77 | 5250 | 0.5246 | |
|
| 0.3843 | 84.62 | 5500 | 0.5244 | |
|
| 0.3843 | 88.46 | 5750 | 0.5252 | |
|
| 0.3731 | 92.31 | 6000 | 0.5092 | |
|
| 0.3731 | 96.15 | 6250 | 0.5098 | |
|
| 0.3698 | 100.0 | 6500 | 0.5357 | |
|
| 0.3698 | 103.85 | 6750 | 0.5315 | |
|
| 0.363 | 107.69 | 7000 | 0.5297 | |
|
| 0.363 | 111.54 | 7250 | 0.5429 | |
|
| 0.358 | 115.38 | 7500 | 0.5418 | |
|
| 0.358 | 119.23 | 7750 | 0.5483 | |
|
| 0.3539 | 123.08 | 8000 | 0.5449 | |
|
| 0.3539 | 126.92 | 8250 | 0.5466 | |
|
| 0.3503 | 130.77 | 8500 | 0.5505 | |
|
| 0.3503 | 134.62 | 8750 | 0.5402 | |
|
| 0.346 | 138.46 | 9000 | 0.5372 | |
|
| 0.346 | 142.31 | 9250 | 0.5547 | |
|
| 0.3421 | 146.15 | 9500 | 0.5650 | |
|
| 0.3421 | 150.0 | 9750 | 0.5544 | |
|
| 0.3376 | 153.85 | 10000 | 0.5594 | |
|
| 0.3376 | 157.69 | 10250 | 0.5624 | |
|
| 0.3331 | 161.54 | 10500 | 0.5574 | |
|
| 0.3331 | 165.38 | 10750 | 0.5605 | |
|
| 0.3285 | 169.23 | 11000 | 0.5710 | |
|
| 0.3285 | 173.08 | 11250 | 0.5671 | |
|
| 0.3253 | 176.92 | 11500 | 0.5561 | |
|
| 0.3253 | 180.77 | 11750 | 0.5677 | |
|
| 0.3233 | 184.62 | 12000 | 0.5841 | |
|
| 0.3233 | 188.46 | 12250 | 0.5770 | |
|
| 0.3203 | 192.31 | 12500 | 0.5705 | |
|
| 0.3203 | 196.15 | 12750 | 0.5642 | |
|
| 0.317 | 200.0 | 13000 | 0.5830 | |
|
| 0.317 | 203.85 | 13250 | 0.5800 | |
|
| 0.3132 | 207.69 | 13500 | 0.5833 | |
|
| 0.3132 | 211.54 | 13750 | 0.5658 | |
|
| 0.31 | 215.38 | 14000 | 0.5874 | |
|
| 0.31 | 219.23 | 14250 | 0.5911 | |
|
| 0.3084 | 223.08 | 14500 | 0.5907 | |
|
| 0.3084 | 226.92 | 14750 | 0.5982 | |
|
| 0.3046 | 230.77 | 15000 | 0.5962 | |
|
| 0.3046 | 234.62 | 15250 | 0.5846 | |
|
| 0.3003 | 238.46 | 15500 | 0.5886 | |
|
| 0.3003 | 242.31 | 15750 | 0.6019 | |
|
| 0.2995 | 246.15 | 16000 | 0.6022 | |
|
| 0.2995 | 250.0 | 16250 | 0.5986 | |
|
| 0.2985 | 253.85 | 16500 | 0.5994 | |
|
| 0.2985 | 257.69 | 16750 | 0.5967 | |
|
| 0.2925 | 261.54 | 17000 | 0.5928 | |
|
| 0.2925 | 265.38 | 17250 | 0.6138 | |
|
| 0.2911 | 269.23 | 17500 | 0.6000 | |
|
| 0.2911 | 273.08 | 17750 | 0.6025 | |
|
| 0.2909 | 276.92 | 18000 | 0.5917 | |
|
| 0.2909 | 280.77 | 18250 | 0.6016 | |
|
| 0.2875 | 284.62 | 18500 | 0.6151 | |
|
| 0.2875 | 288.46 | 18750 | 0.6035 | |
|
| 0.2866 | 292.31 | 19000 | 0.6019 | |
|
| 0.2866 | 296.15 | 19250 | 0.6014 | |
|
| 0.2821 | 300.0 | 19500 | 0.6029 | |
|
| 0.2821 | 303.85 | 19750 | 0.5953 | |
|
| 0.2814 | 307.69 | 20000 | 0.6202 | |
|
| 0.2814 | 311.54 | 20250 | 0.5953 | |
|
| 0.2798 | 315.38 | 20500 | 0.6153 | |
|
| 0.2798 | 319.23 | 20750 | 0.6232 | |
|
| 0.2766 | 323.08 | 21000 | 0.6175 | |
|
| 0.2766 | 326.92 | 21250 | 0.6162 | |
|
| 0.2755 | 330.77 | 21500 | 0.6047 | |
|
| 0.2755 | 334.62 | 21750 | 0.6052 | |
|
| 0.2742 | 338.46 | 22000 | 0.6138 | |
|
| 0.2742 | 342.31 | 22250 | 0.6225 | |
|
| 0.2746 | 346.15 | 22500 | 0.6015 | |
|
| 0.2746 | 350.0 | 22750 | 0.6029 | |
|
| 0.2716 | 353.85 | 23000 | 0.6105 | |
|
| 0.2716 | 357.69 | 23250 | 0.6132 | |
|
| 0.2697 | 361.54 | 23500 | 0.6129 | |
|
| 0.2697 | 365.38 | 23750 | 0.6045 | |
|
| 0.2704 | 369.23 | 24000 | 0.6155 | |
|
| 0.2704 | 373.08 | 24250 | 0.6075 | |
|
| 0.2694 | 376.92 | 24500 | 0.6154 | |
|
| 0.2694 | 380.77 | 24750 | 0.6263 | |
|
| 0.2672 | 384.62 | 25000 | 0.6181 | |
|
| 0.2672 | 388.46 | 25250 | 0.6185 | |
|
| 0.2649 | 392.31 | 25500 | 0.6131 | |
|
| 0.2649 | 396.15 | 25750 | 0.6113 | |
|
| 0.2641 | 400.0 | 26000 | 0.6151 | |
|
| 0.2641 | 403.85 | 26250 | 0.6219 | |
|
| 0.2642 | 407.69 | 26500 | 0.6228 | |
|
| 0.2642 | 411.54 | 26750 | 0.6258 | |
|
| 0.2621 | 415.38 | 27000 | 0.6161 | |
|
| 0.2621 | 419.23 | 27250 | 0.6316 | |
|
| 0.2634 | 423.08 | 27500 | 0.6159 | |
|
| 0.2634 | 426.92 | 27750 | 0.6192 | |
|
| 0.2611 | 430.77 | 28000 | 0.6210 | |
|
| 0.2611 | 434.62 | 28250 | 0.6246 | |
|
| 0.2593 | 438.46 | 28500 | 0.6142 | |
|
| 0.2593 | 442.31 | 28750 | 0.6157 | |
|
| 0.26 | 446.15 | 29000 | 0.6198 | |
|
| 0.26 | 450.0 | 29250 | 0.6182 | |
|
| 0.262 | 453.85 | 29500 | 0.6188 | |
|
| 0.262 | 457.69 | 29750 | 0.6223 | |
|
| 0.2616 | 461.54 | 30000 | 0.6228 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.14.1 |
|
|
