Edit model card

SpeechT5 TTS with Andrej Karpathy voice

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

  • Loss: 0.4266

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

Training results

Training Loss Epoch Step Validation Loss
0.3572 250.0 1000 0.4057
0.3299 500.0 2000 0.4226
0.3136 750.0 3000 0.4277
0.3165 1000.0 4000 0.4266

Framework versions

  • Transformers 4.45.0.dev0
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
10
Safetensors
Model size
144M params
Tensor type
F32
·
Inference Examples
Inference API (serverless) is not available, repository is disabled.

Model tree for Fafadalilian/speecht5_tts_voxpopuli_nl

Finetuned
this model