metadata

library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - common_voice_12_0
model-index:
  - name: speecht5_finetuned_voxpopuli_nl
    results: []
language:
  - sw
  - en

speecht5_finetuned_voxpopuli_nl

This model is a fine-tuned version of microsoft/speecht5_tts on the common_voice_12_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.5539

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: 3000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6223	3.2389	1000	0.5753
0.5906	6.4777	2000	0.5568
0.5857	9.7166	3000	0.5539

Framework versions

Transformers 4.44.2
Pytorch 2.1.0
Datasets 2.21.0
Tokenizers 0.19.1