SpeechT5 TTS Kurdish - Kurmanji

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

  • Loss: 0.5395

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: 16000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5187 27.5862 4000 0.5304
0.494 55.1724 8000 0.5374
0.4869 82.7586 12000 0.5350
0.4957 110.3448 16000 0.5395

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.1+cu118
  • Datasets 2.19.2
  • Tokenizers 0.19.1
Downloads last month
14
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 roshna-omer/speecht5_tts_krd-kmr_CV17.0

Finetuned
(857)
this model

Dataset used to train roshna-omer/speecht5_tts_krd-kmr_CV17.0