Edit model card

SpeechT5 Romanian

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

  • Loss: 0.4508

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: 4
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • 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: 1200

Training results

Training Loss Epoch Step Validation Loss
0.5438 4.22 400 0.4808
0.5009 8.43 800 0.4563
0.4886 12.65 1200 0.4508

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3
Downloads last month
15
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 gigant/speecht5_finetuned_voxpopuli_ro_audio_course_v2

Finetuned
(747)
this model

Dataset used to train gigant/speecht5_finetuned_voxpopuli_ro_audio_course_v2

Space using gigant/speecht5_finetuned_voxpopuli_ro_audio_course_v2 1