speecht5_finetuned_voxpopuli_et

theoldmandthesea/speecht5_finetuned_voxpopuli_et

speecht5_finetuned_voxpopuli_et is a text-to-speech model from theoldmandthesea. 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

5% of all-time downloads

All-time downloads

295

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: Jul 29, 2023
Updated: Jul 29, 2023
SHA: ee2ff0a2

Datasets

voxpopuli

Model card

From the Hugging Face model README

speecht5_finetuned_voxpopuli_et

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

Loss: 0.4818

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: 20
training_steps: 300

Training results

Training Loss	Epoch	Step	Validation Loss
0.6529	5.26	50	0.5621
0.6028	10.53	100	0.5290
0.5524	15.79	150	0.4993
0.5339	21.05	200	0.4866
0.5212	26.32	250	0.4827
0.5239	31.58	300	0.4818

Framework versions

Transformers 4.30.2
Pytorch 2.0.0
Datasets 2.1.0
Tokenizers 0.13.3

Task: Text-to-Speech
Library: transformers
Type: speecht5
License: mit
Created: Jul 29, 2023
Updated: Jul 29, 2023