Downloads · 30 days
100
8% of all-time downloads
speecht5_finetuned_multilingual_librispeech_italian9h
ClementXie/speecht5_finetuned_multilingual_librispeech_italian9h
speecht5_finetuned_multilingual_librispeech_italian9h is a text-to-speech model from ClementXie. Use it when you need text read aloud. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
1.3K
Public
Parameters
144M
3.5 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin578 MB · 50%
At a glance
- Task
- Text-to-Speech
- Library
- transformers
- Model type
- speecht5
- Access
- Public
- Created
- Aug 6, 2023
- Updated
- Sep 20, 2023
- SHA
- 43b5fca7
Base models
Model card
From the Hugging Face model README
<!-- 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-finetuned-multilingual_librispeech
This model is a fine-tuned version of microsoft/speecht5_tts on the multilingual_librispeech dataset. It achieves the following results on the evaluation set:
- Loss: 0.4342
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: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5378 | 7.75 | 250 | 0.4721 |
| 0.4872 | 15.5 | 500 | 0.4424 |
| 0.4766 | 23.26 | 750 | 0.4363 |
| 0.4784 | 31.01 | 1000 | 0.4342 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 1.13.1
- Datasets 2.14.3
- Tokenizers 0.13.2
- Task
- Text-to-Speech
- Library
- transformers
- Type
- speecht5
- Languages
- ita
- Created
- Aug 6, 2023
- Updated
- Sep 20, 2023