speecht5_finetuned_kaab_tts_full

kaab4321/speecht5_finetuned_kaab_tts_full

speecht5_finetuned_kaab_tts_full is a text-to-audio model from kaab4321. Use it for the text-to-audio task on the model card, and read the license before you ship it in a product. 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

9% of all-time downloads

All-time downloads

181

Public

Parameters

144M

28.9 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors578 MB · 100%

At a glance

Task: Text-to-Audio
Library: transformers
License: mit
Model type: speecht5
Access: Public
Created: Feb 25, 2025
Updated: Feb 26, 2025
SHA: 1cf271d2

Base models

microsoft/speecht5_tts

Model card

From the Hugging Face model README

speecht5_finetuned_kaab_tts_full

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: 0.4089

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: 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: 100
training_steps: 50000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5299	0.3891	1000	0.4921
0.497	0.7782	2000	0.4712
0.4844	1.1669	3000	0.4632
0.4909	1.5560	4000	0.4639
0.4781	1.9451	5000	0.4688
0.4724	2.3338	6000	0.4516
0.4758	2.7229	7000	0.4528
0.4695	3.1117	8000	0.4449
0.4634	3.5008	9000	0.4492
0.4675	3.8898	10000	0.4394
0.4553	4.2786	11000	0.4398
0.4595	4.6677	12000	0.4371
0.4571	5.0564	13000	0.4366
0.4551	5.4455	14000	0.4343
0.4595	5.8346	15000	0.4343
0.4495	6.2233	16000	0.4312
0.4491	6.6124	17000	0.4300
0.4299	7.0012	18000	0.4288
0.4471	7.3903	19000	0.4274
0.4417	7.7793	20000	0.4283
0.4432	8.1681	21000	0.4248
0.4426	8.5572	22000	0.4264
0.4436	8.9463	23000	0.4243
0.439	9.3350	24000	0.4254
0.4368	9.7241	25000	0.4221
0.4326	10.1128	26000	0.4200
0.4386	10.5019	27000	0.4230
0.4338	10.8910	28000	0.4198
0.4274	11.2798	29000	0.4186
0.4364	11.6688	30000	0.4184
0.4273	12.0576	31000	0.4169
0.4333	12.4467	32000	0.4174
0.4303	12.8358	33000	0.4145
0.4257	13.2245	34000	0.4166
0.4311	13.6136	35000	0.4140
0.408	14.0023	36000	0.4129
0.4253	14.3914	37000	0.4124
0.4237	14.7805	38000	0.4119
0.4287	15.1693	39000	0.4114
0.4217	15.5583	40000	0.4103
0.4202	15.9474	41000	0.4110
0.415	16.3362	42000	0.4111
0.4156	16.7253	43000	0.4095
0.4108	17.1140	44000	0.4095
0.415	17.5031	45000	0.4092
0.4178	17.8922	46000	0.4085
0.4168	18.2809	47000	0.4099
0.4192	18.6700	48000	0.4087
0.4114	19.0588	49000	0.4088
0.4111	19.4478	50000	0.4089

Framework versions

Transformers 4.49.0
Pytorch 2.6.0+cu118
Datasets 3.3.2
Tokenizers 0.21.0

Task: Text-to-Audio
Library: transformers
Type: speecht5
License: mit
Created: Feb 25, 2025
Updated: Feb 26, 2025