README.md

metadata

language:
  - ckb
tags:
  - tts
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
model-index:
  - name: SpeechT5 TTS ckb
    results: []

SpeechT5 TTS ckb

This model is a fine-tuned version of [speecht5_tts - Saber Molaei](https://huggingface.co/speecht5_tts - Saber Molaei) on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5855

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: 4
• 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: 500
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6452	7.41	1000	0.5855

Framework versions

• Transformers 4.29.0.dev0
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3