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

Loss: 0.3252

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: 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
0.3684	5.5571	1000	0.3399
0.3462	11.1114	2000	0.3303
0.35	16.6685	3000	0.3261
0.346	22.2228	4000	0.3252

Framework versions

Transformers 4.52.0
Pytorch 2.10.0+cu128
Datasets 3.6.0
Tokenizers 0.21.4

EvgenyShivchenkoUIT/speecht5_finetuned_haitian_creole-without-spec-token

SpeechT5 TTS HAT

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

EvgenyShivchenkoUIT/
speecht5_finetuned_haitian_creole-without-spec-token