Hugging Face's logo

NMutangana
/
speecht5_tts_common_voice_kinyarwanda

Text-to-Audio
Transformers
TensorBoard
Safetensors
Kinyarwanda
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_tts_common_voice_kinyarwanda / README.md
NMutangana's picture
NMutangana
End of training
12c06a0 verified
preview code
|
raw
history blame
No virus
1.47 kB
metadata
language:
  - rw
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
model-index:
  - name: SpeechT5 TTS Kinyarwanda
    results: []

SpeechT5 TTS Kinyarwanda

This model is a fine-tuned version of microsoft/speecht5_tts on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.5317
  • eval_runtime: 32.2362
  • eval_samples_per_second: 45.446
  • eval_steps_per_second: 5.708
  • epoch: 2.4272
  • step: 1000

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: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • 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: 4000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.41.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1