speecht5_tts_commonvoice_en_04

Avitas8485/speecht5_tts_commonvoice_en_04

speecht5_tts_commonvoice_en_04 is a text-to-speech model from Avitas8485. Use it when you need text read aloud. It is set up for transformers. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

3% of all-time downloads

All-time downloads

865

Public

Repo size

4.1 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin585 MB · 100%

At a glance

Task: Text-to-Speech
Library: transformers
License: mit
Model type: speecht5
Access: Public
Created: Jun 21, 2023
Updated: Sep 12, 2023
SHA: 7ce7feda

Base models

Avitas8485/speecht5_tts_commonvoice_en_03

Datasets

lj_speech

Model card

From the Hugging Face model README

speecht5_tts_commonvoice_en_04

This model is a fine-tuned version of Avitas8485/speecht5_tts_commonvoice_en_03 on the ljspeech dataset. It achieves the following results on the evaluation set:

Loss: 0.3719

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: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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
0.4105	1.36	1000	0.3789
0.409	2.71	2000	0.3753
0.4076	4.07	3000	0.3735
0.4055	5.43	4000	0.3719

Framework versions

Transformers 4.30.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.13.0
Tokenizers 0.13.3

Task: Text-to-Speech
Library: transformers
Type: speecht5
License: mit
Languages: en
Created: Jun 21, 2023
Updated: Sep 12, 2023