README.md

metadata

license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - facebook/voxpopuli
model-index:
  - name: speecht5_finetuned_voxpopuli_nl_1Ksamples
    results:
      - task:
          name: Text to Speech
          type: text-to-speech
        dataset:
          name: facebook/voxpopuli
          type: facebook/voxpopuli
          config: lt
          split: train
          args: lt
        metrics:
          - name: loss
            type: loss
            value: None
pipeline_tag: text-to-speech

speec T5 LT - Abhinay Poloju

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

• Loss: 0.4718

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: 8
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• 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
0.4717	125.0	1000	0.4747
0.4543	250.0	2000	0.4715
0.4451	375.0	3000	0.4734
0.4417	500.0	4000	0.4718

Framework versions

• Transformers 4.41.0.dev0
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.19.1