omarViga
/

SpeechT5_TTS_Spanish

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

SpeechT5 TTS Spanish

This model is a fine-tuned version of microsoft/speecht5_tts on the mabama-v6 dataset. It achieves the following results on the evaluation set:

Loss: 0.4673

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: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
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
0.4472	125.0	1000	0.5155
0.4113	250.0	2000	0.4834
0.3906	375.0	3000	0.4680
0.3902	500.0	4000	0.4673

Framework versions

Transformers 4.52.0.dev0
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

Downloads last month: 14

Safetensors

Model size

144M params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support

Model tree for omarViga/SpeechT5_TTS_Spanish

Base model

microsoft/speecht5_tts

Finetuned

(1075)

this model

Dataset used to train omarViga/SpeechT5_TTS_Spanish

Space using omarViga/SpeechT5_TTS_Spanish 1

Evaluation results

Metadata error: specify a dataset to view leaderboard