Instructions to use avdeep/tts_3000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use avdeep/tts_3000 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="avdeep/tts_3000")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForTextToSpectrogram processor = AutoProcessor.from_pretrained("avdeep/tts_3000") model = AutoModelForTextToSpectrogram.from_pretrained("avdeep/tts_3000", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from avdeep/tts_3000: direct link, hf CLI and curl.
- Browser
- Download file 6.24 kB
-
https://huggingface.co/avdeep/tts_3000/resolve/main/README.md
- Command line
-
hf download hf://avdeep/tts_3000/README.md
-
curl -L -o README.md https://huggingface.co/avdeep/tts_3000/resolve/main/README.md
6.24 kB
| library_name: transformers | |
| license: mit | |
| base_model: microsoft/speecht5_tts | |
| tags: | |
| - generated_from_trainer | |
| model-index: | |
| - name: tts_3000 | |
| 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. --> | |
| # tts_3000 | |
| This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.4958 | |
| ## 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: 2e-05 | |
| - train_batch_size: 16 | |
| - eval_batch_size: 2 | |
| - seed: 42 | |
| - optimizer: Use OptimizerNames.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 | |
| - num_epochs: 10 | |
| - mixed_precision_training: Native AMP | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | | |
| |:-------------:|:------:|:----:|:---------------:| | |
| | 0.9692 | 0.1074 | 100 | 0.8755 | | |
| | 0.7909 | 0.2148 | 200 | 0.7229 | | |
| | 0.6814 | 0.3222 | 300 | 0.6576 | | |
| | 0.7051 | 0.4296 | 400 | 0.6267 | | |
| | 0.6291 | 0.5371 | 500 | 0.6020 | | |
| | 0.6234 | 0.6445 | 600 | 0.5874 | | |
| | 0.6015 | 0.7519 | 700 | 0.5753 | | |
| | 0.5888 | 0.8593 | 800 | 0.5715 | | |
| | 0.6018 | 0.9667 | 900 | 0.5699 | | |
| | 0.5807 | 1.0741 | 1000 | 0.5620 | | |
| | 0.5711 | 1.1815 | 1100 | 0.5572 | | |
| | 0.5634 | 1.2889 | 1200 | 0.5525 | | |
| | 0.5703 | 1.3963 | 1300 | 0.5487 | | |
| | 0.5549 | 1.5038 | 1400 | 0.5457 | | |
| | 0.5441 | 1.6112 | 1500 | 0.5422 | | |
| | 0.5578 | 1.7186 | 1600 | 0.5420 | | |
| | 0.5779 | 1.8260 | 1700 | 0.5395 | | |
| | 0.5608 | 1.9334 | 1800 | 0.5370 | | |
| | 0.5404 | 2.0408 | 1900 | 0.5352 | | |
| | 0.5494 | 2.1482 | 2000 | 0.5357 | | |
| | 0.539 | 2.2556 | 2100 | 0.5333 | | |
| | 0.5471 | 2.3631 | 2200 | 0.5302 | | |
| | 0.537 | 2.4705 | 2300 | 0.5274 | | |
| | 0.5429 | 2.5779 | 2400 | 0.5287 | | |
| | 0.5348 | 2.6853 | 2500 | 0.5293 | | |
| | 0.546 | 2.7927 | 2600 | 0.5291 | | |
| | 0.5322 | 2.9001 | 2700 | 0.5231 | | |
| | 0.5377 | 3.0075 | 2800 | 0.5232 | | |
| | 0.5282 | 3.1149 | 2900 | 0.5259 | | |
| | 0.5346 | 3.2223 | 3000 | 0.5204 | | |
| | 0.5244 | 3.3298 | 3100 | 0.5179 | | |
| | 0.5297 | 3.4372 | 3200 | 0.5228 | | |
| | 0.5274 | 3.5446 | 3300 | 0.5161 | | |
| | 0.53 | 3.6520 | 3400 | 0.5159 | | |
| | 0.5253 | 3.7594 | 3500 | 0.5136 | | |
| | 0.5338 | 3.8668 | 3600 | 0.5134 | | |
| | 0.5445 | 3.9742 | 3700 | 0.5204 | | |
| | 0.5284 | 4.0816 | 3800 | 0.5132 | | |
| | 0.5333 | 4.1890 | 3900 | 0.5140 | | |
| | 0.5209 | 4.2965 | 4000 | 0.5106 | | |
| | 0.5311 | 4.4039 | 4100 | 0.5126 | | |
| | 0.5174 | 4.5113 | 4200 | 0.5094 | | |
| | 0.5263 | 4.6187 | 4300 | 0.5090 | | |
| | 0.5195 | 4.7261 | 4400 | 0.5090 | | |
| | 0.5212 | 4.8335 | 4500 | 0.5064 | | |
| | 0.5211 | 4.9409 | 4600 | 0.5080 | | |
| | 0.5379 | 5.0483 | 4700 | 0.5076 | | |
| | 0.5284 | 5.1557 | 4800 | 0.5092 | | |
| | 0.5164 | 5.2632 | 4900 | 0.5065 | | |
| | 0.5244 | 5.3706 | 5000 | 0.5075 | | |
| | 0.5292 | 5.4780 | 5100 | 0.5070 | | |
| | 0.5116 | 5.5854 | 5200 | 0.5055 | | |
| | 0.5444 | 5.6928 | 5300 | 0.5059 | | |
| | 0.5126 | 5.8002 | 5400 | 0.5034 | | |
| | 0.5174 | 5.9076 | 5500 | 0.5073 | | |
| | 0.5086 | 6.0150 | 5600 | 0.5035 | | |
| | 0.5098 | 6.1224 | 5700 | 0.5048 | | |
| | 0.5147 | 6.2299 | 5800 | 0.5057 | | |
| | 0.5085 | 6.3373 | 5900 | 0.5030 | | |
| | 0.5155 | 6.4447 | 6000 | 0.5016 | | |
| | 0.5273 | 6.5521 | 6100 | 0.5032 | | |
| | 0.5154 | 6.6595 | 6200 | 0.5015 | | |
| | 0.5168 | 6.7669 | 6300 | 0.5013 | | |
| | 0.5199 | 6.8743 | 6400 | 0.5018 | | |
| | 0.5299 | 6.9817 | 6500 | 0.5014 | | |
| | 0.5166 | 7.0892 | 6600 | 0.5030 | | |
| | 0.5092 | 7.1966 | 6700 | 0.5006 | | |
| | 0.5117 | 7.3040 | 6800 | 0.5016 | | |
| | 0.5132 | 7.4114 | 6900 | 0.5002 | | |
| | 0.5196 | 7.5188 | 7000 | 0.4989 | | |
| | 0.5085 | 7.6262 | 7100 | 0.4989 | | |
| | 0.5097 | 7.7336 | 7200 | 0.4995 | | |
| | 0.51 | 7.8410 | 7300 | 0.4982 | | |
| | 0.5095 | 7.9484 | 7400 | 0.4978 | | |
| | 0.5172 | 8.0559 | 7500 | 0.5002 | | |
| | 0.5151 | 8.1633 | 7600 | 0.4991 | | |
| | 0.512 | 8.2707 | 7700 | 0.4997 | | |
| | 0.4991 | 8.3781 | 7800 | 0.4989 | | |
| | 0.5113 | 8.4855 | 7900 | 0.4980 | | |
| | 0.5134 | 8.5929 | 8000 | 0.4975 | | |
| | 0.5148 | 8.7003 | 8100 | 0.4969 | | |
| | 0.514 | 8.8077 | 8200 | 0.4980 | | |
| | 0.5119 | 8.9151 | 8300 | 0.4989 | | |
| | 0.5054 | 9.0226 | 8400 | 0.4967 | | |
| | 0.5088 | 9.1300 | 8500 | 0.4968 | | |
| | 0.5067 | 9.2374 | 8600 | 0.4961 | | |
| | 0.5148 | 9.3448 | 8700 | 0.4976 | | |
| | 0.5098 | 9.4522 | 8800 | 0.4965 | | |
| | 0.5035 | 9.5596 | 8900 | 0.4965 | | |
| | 0.5111 | 9.6670 | 9000 | 0.4973 | | |
| | 0.507 | 9.7744 | 9100 | 0.4963 | | |
| | 0.5048 | 9.8818 | 9200 | 0.4963 | | |
| | 0.4992 | 9.9893 | 9300 | 0.4958 | | |
| ### Framework versions | |
| - Transformers 4.48.2 | |
| - Pytorch 2.5.1+cu124 | |
| - Datasets 3.2.0 | |
| - Tokenizers 0.21.0 | |