SpeechT5 TTS Tunisien

This model is a fine-tuned version of MBZUAI/speecht5_tts_clartts_ar on the datasetSTT-TTS dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5464

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • 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
0.544 14.2857 200 0.6401
0.4869 28.5714 400 0.5907
0.4384 42.8571 600 0.5684
0.4069 57.1429 800 0.5577
0.3992 71.4286 1000 0.5464

Framework versions

  • Transformers 4.42.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
16
Safetensors
Model size
144M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Arbi-Houssem/speecht5_ar_tn_1.1

Finetuned
(13)
this model

Dataset used to train Arbi-Houssem/speecht5_ar_tn_1.1