speecht5_finetuned_multilingual_librispeech_pl

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

  • Loss: 0.4168

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: 4000

Training results

Training Loss Epoch Step Validation Loss
0.4564 40.82 1000 0.4182
0.4277 81.63 2000 0.4124
0.4233 122.45 3000 0.4173
0.4222 163.27 4000 0.4168

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.13.1
  • Tokenizers 0.13.3
Downloads last month
29
Safetensors
Model size
144M params
Tensor type
F32
ยท
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 Sagicc/speecht5_finetuned_multilingual_librispeech_pl

Finetuned
(856)
this model

Dataset used to train Sagicc/speecht5_finetuned_multilingual_librispeech_pl

Space using Sagicc/speecht5_finetuned_multilingual_librispeech_pl 1