speecht5_finetuned_emirhan_tr

Ramal1/speecht5_finetuned_emirhan_tr

speecht5_finetuned_emirhan_tr is a machine learning model from Ramal1. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.

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

Downloads · 30 days

14% of all-time downloads

All-time downloads

Public

Parameters

144M

2.9 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors578 MB · 100%

At a glance

License: mit
Model type: speecht5
Access: Public
Created: May 10, 2025
Updated: May 10, 2025
SHA: 03eedb48

Base models

microsoft/speecht5_tts

Model card

From the Hugging Face model README

speecht5_finetuned_emirhan_tr

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: 0.3289

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: 0.0001
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: 100
training_steps: 500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5123	0.1091	100	0.4426
0.4166	0.2181	200	0.3831
0.3947	0.3272	300	0.3596
0.3551	0.4362	400	0.3357
0.3476	0.5453	500	0.3289

Framework versions

Transformers 4.42.4
Pytorch 2.7.0+cpu
Datasets 3.5.1
Tokenizers 0.19.1

Type: speecht5
License: mit
Created: May 10, 2025
Updated: May 10, 2025