speecht5_finetuned_English_Technical_Terms_Shabdobhedii

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: 0.4809

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: 4
• 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: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.8309	0.3583	100	0.7287
0.7305	0.7165	200	0.6828
0.6819	1.0748	300	0.6334
0.5878	1.4330	400	0.5213
0.552	1.7913	500	0.4988
0.5496	2.1496	600	0.4908
0.5447	2.5078	700	0.4862
0.5369	2.8661	800	0.4848
0.5327	3.2244	900	0.4823
0.5321	3.5826	1000	0.4809

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.2
• Tokenizers 0.19.1