speecht5_tts_lg

EricPeter/speecht5_tts_lg

speecht5_tts_lg is a text-to-audio model from EricPeter. Use it for the text-to-audio task on the model card, and read the license before you ship it in a product. 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

8% of all-time downloads

All-time downloads

304

Public

Parameters

144M

9.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt1.2 GB · 67%

At a glance

Task: Text-to-Audio
Library: transformers
License: mit
Model type: speecht5
Access: Public
Created: Jan 23, 2024
Updated: Feb 6, 2024
SHA: c14d799a

Base models

microsoft/speecht5_tts

Model card

From the Hugging Face model README

speecht5_tts_lg

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

Loss: 0.3654

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: 24
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
0.4208	14.81	1000	0.3788
0.3912	29.63	2000	0.3669
0.3901	44.44	3000	0.3646
0.3893	59.26	4000	0.3654

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1

Task: Text-to-Audio
Library: transformers
Type: speecht5
License: mit
Created: Jan 23, 2024
Updated: Feb 6, 2024