speecht5_finetuned_common_voice_11_de

sjdata/speecht5_finetuned_common_voice_11_de

speecht5_finetuned_common_voice_11_de is a text-to-speech model from sjdata. 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

1.7K

Public

Repo size

3.5 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin578 MB · 100%

At a glance

Task: Text-to-Speech
Library: transformers
License: mit
Model type: speecht5
Access: Public
Created: Jul 12, 2023
Updated: Jul 12, 2023
SHA: c6e6ee0b

Datasets

mozilla-foundation/common_voice_11_0

Model card

From the Hugging Face model README

SpeechT5 Common Voice German Finetune

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

Loss: 0.4921

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
0.5533	17.58	1000	0.5283
0.5163	35.16	2000	0.5030
0.5097	52.75	3000	0.4981
0.5025	70.33	4000	0.4921

Framework versions

Transformers 4.31.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3

Task: Text-to-Speech
Library: transformers
Type: speecht5
License: mit
Languages: de
Created: Jul 12, 2023
Updated: Jul 12, 2023