Speecht5 Finetuned Commonvoice Ru Translit

🚀 SpeechT5 - Russian translit

This model is a fine - tuned version of microsoft/speecht5_tts for text - to - speech tasks, specifically trained on the Common Voice 13 dataset.

🚀 Quick Start

This model is a fine - tuned version of microsoft/speecht5_tts on the Common Voice 13 dataset. It achieves a loss of 0.4853 on the evaluation set.

✨ Features

• The input should be Russian text in transliterated form (using the transliterate package).
• This is just a test for the hands - on exercise of the HF Audio Course and is not intended for actual use.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

No code examples are provided in the original document, so this section is skipped.

📚 Documentation

Model description

Input should be a Russian text in transliterated form (use the transliterate package). This is just a test for the hands - on exercise of the HF Audio Course! Not intended for actual use!

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: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9, 0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 400
• training_steps: 2000

Training results

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3

🔧 Technical Details

The model is a fine - tuned version of microsoft/speecht5_tts on the Common Voice 13 dataset. The training process uses specific hyperparameters and an Adam optimizer with a linear learning rate scheduler.

📄 License

This model is released under the MIT license.