metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_tts_wolof
results: []
speecht5_tts_wolof
This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2993
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1192 | 0.5952 | 50 | 0.4722 |
| 0.9979 | 1.1905 | 100 | 0.4139 |
| 0.8933 | 1.7857 | 150 | 0.3900 |
| 0.8718 | 2.3810 | 200 | 0.3818 |
| 0.8246 | 2.9762 | 250 | 0.3758 |
| 0.8062 | 3.5714 | 300 | 0.3615 |
| 0.7931 | 4.1667 | 350 | 0.3546 |
| 0.756 | 4.7619 | 400 | 0.3469 |
| 0.7462 | 5.3571 | 450 | 0.3393 |
| 0.7311 | 5.9524 | 500 | 0.3358 |
| 0.7298 | 6.5476 | 550 | 0.3315 |
| 0.7234 | 7.1429 | 600 | 0.3300 |
| 0.7199 | 7.7381 | 650 | 0.3287 |
| 0.697 | 8.3333 | 700 | 0.3250 |
| 0.7006 | 8.9286 | 750 | 0.3231 |
| 0.7081 | 9.5238 | 800 | 0.3218 |
| 0.6998 | 10.1190 | 850 | 0.3196 |
| 0.7074 | 10.7143 | 900 | 0.3202 |
| 0.6831 | 11.3095 | 950 | 0.3161 |
| 0.6899 | 11.9048 | 1000 | 0.3169 |
| 0.6935 | 12.5 | 1050 | 0.3160 |
| 0.6778 | 13.0952 | 1100 | 0.3145 |
| 0.6701 | 13.6905 | 1150 | 0.3122 |
| 0.6792 | 14.2857 | 1200 | 0.3121 |
| 0.6668 | 14.8810 | 1250 | 0.3117 |
| 0.6682 | 15.4762 | 1300 | 0.3120 |
| 0.6742 | 16.0714 | 1350 | 0.3103 |
| 0.6759 | 16.6667 | 1400 | 0.3103 |
| 0.6776 | 17.2619 | 1450 | 0.3100 |
| 0.6699 | 17.8571 | 1500 | 0.3099 |
| 0.6744 | 18.4524 | 1550 | 0.3092 |
| 0.6636 | 19.0476 | 1600 | 0.3083 |
| 0.6552 | 19.6429 | 1650 | 0.3067 |
| 0.6618 | 20.2381 | 1700 | 0.3074 |
| 0.6482 | 20.8333 | 1750 | 0.3059 |
| 0.6684 | 21.4286 | 1800 | 0.3063 |
| 0.6726 | 22.0238 | 1850 | 0.3060 |
| 0.648 | 22.6190 | 1900 | 0.3053 |
| 0.6542 | 23.2143 | 1950 | 0.3043 |
| 0.6516 | 23.8095 | 2000 | 0.3050 |
| 0.6654 | 24.4048 | 2050 | 0.3059 |
| 0.6556 | 25.0 | 2100 | 0.3050 |
| 0.6493 | 25.5952 | 2150 | 0.3051 |
| 0.6504 | 26.1905 | 2200 | 0.3033 |
| 0.6463 | 26.7857 | 2250 | 0.3033 |
| 0.655 | 27.3810 | 2300 | 0.3028 |
| 0.6474 | 27.9762 | 2350 | 0.3030 |
| 0.6434 | 28.5714 | 2400 | 0.3022 |
| 0.6427 | 29.1667 | 2450 | 0.3027 |
| 0.6611 | 29.7619 | 2500 | 0.3030 |
| 0.6536 | 30.3571 | 2550 | 0.3026 |
| 0.6478 | 30.9524 | 2600 | 0.3011 |
| 0.6471 | 31.5476 | 2650 | 0.3021 |
| 0.6424 | 32.1429 | 2700 | 0.3014 |
| 0.6424 | 32.7381 | 2750 | 0.3012 |
| 0.645 | 33.3333 | 2800 | 0.3010 |
| 0.6454 | 33.9286 | 2850 | 0.3010 |
| 0.6373 | 34.5238 | 2900 | 0.3006 |
| 0.6409 | 35.1190 | 2950 | 0.3005 |
| 0.6382 | 35.7143 | 3000 | 0.3007 |
| 0.6377 | 36.3095 | 3050 | 0.3005 |
| 0.643 | 36.9048 | 3100 | 0.3007 |
| 0.6383 | 37.5 | 3150 | 0.2999 |
| 0.6396 | 38.0952 | 3200 | 0.2998 |
| 0.6413 | 38.6905 | 3250 | 0.3006 |
| 0.6368 | 39.2857 | 3300 | 0.2998 |
| 0.6452 | 39.8810 | 3350 | 0.3006 |
| 0.6425 | 40.4762 | 3400 | 0.3000 |
| 0.6406 | 41.0714 | 3450 | 0.3001 |
| 0.657 | 41.6667 | 3500 | 0.2996 |
| 0.6353 | 42.2619 | 3550 | 0.2998 |
| 0.6369 | 42.8571 | 3600 | 0.2999 |
| 0.6314 | 43.4524 | 3650 | 0.2997 |
| 0.634 | 44.0476 | 3700 | 0.2992 |
| 0.6506 | 44.6429 | 3750 | 0.3010 |
| 0.63 | 45.2381 | 3800 | 0.2993 |
| 0.6395 | 45.8333 | 3850 | 0.2997 |
| 0.6393 | 46.4286 | 3900 | 0.2983 |
| 0.6344 | 47.0238 | 3950 | 0.2998 |
| 0.6432 | 47.6190 | 4000 | 0.2993 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0