Hugging Face's logo

Hawoly18
/
speecht5_tts_wolof

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community

speecht5_tts_wolof

This model is a fine-tuned version of Moustapha91/speecht5_finetuned_wo_v1 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2943

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Use 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
0.9404 0.5952 50 0.4362
0.8342 1.1905 100 0.3784
0.7869 1.7857 150 0.3627
0.7841 2.3810 200 0.3546
0.762 2.9762 250 0.3489
0.7487 3.5714 300 0.3431
0.7423 4.1667 350 0.3392
0.7211 4.7619 400 0.3362
0.7147 5.3571 450 0.3304
0.7097 5.9524 500 0.3266
0.7058 6.5476 550 0.3223
0.6929 7.1429 600 0.3198
0.6887 7.7381 650 0.3152
0.664 8.3333 700 0.3131
0.6736 8.9286 750 0.3115
0.6767 9.5238 800 0.3105
0.6722 10.1190 850 0.3095
0.6702 10.7143 900 0.3075
0.6615 11.3095 950 0.3058
0.6654 11.9048 1000 0.3063
0.6682 12.5 1050 0.3083
0.6607 13.0952 1100 0.3051
0.6514 13.6905 1150 0.3042
0.6605 14.2857 1200 0.3041
0.6509 14.8810 1250 0.3028
0.6556 15.4762 1300 0.3025
0.6477 16.0714 1350 0.3019
0.6489 16.6667 1400 0.3011
0.6567 17.2619 1450 0.3007
0.6533 17.8571 1500 0.3016
0.6489 18.4524 1550 0.3009
0.6454 19.0476 1600 0.3002
0.6354 19.6429 1650 0.2992
0.645 20.2381 1700 0.2996
0.6376 20.8333 1750 0.2993
0.6472 21.4286 1800 0.2991
0.6571 22.0238 1850 0.2995
0.6333 22.6190 1900 0.2986
0.6323 23.2143 1950 0.2973
0.6314 23.8095 2000 0.2980
0.6437 24.4048 2050 0.2980
0.6383 25.0 2100 0.2977
0.6314 25.5952 2150 0.2978
0.6309 26.1905 2200 0.2965
0.6365 26.7857 2250 0.2965
0.6406 27.3810 2300 0.2966
0.6286 27.9762 2350 0.2968
0.6279 28.5714 2400 0.2963
0.6304 29.1667 2450 0.2967
0.6457 29.7619 2500 0.2960
0.6372 30.3571 2550 0.2958
0.6338 30.9524 2600 0.2952
0.6325 31.5476 2650 0.2956
0.6313 32.1429 2700 0.2951
0.6345 32.7381 2750 0.2956
0.6289 33.3333 2800 0.2949
0.6264 33.9286 2850 0.2947
0.6302 34.5238 2900 0.2952
0.6248 35.1190 2950 0.2945
0.626 35.7143 3000 0.2945
0.6248 36.3095 3050 0.2947
0.6306 36.9048 3100 0.2943
0.6258 37.5 3150 0.2944
0.6318 38.0952 3200 0.2947
0.6279 38.6905 3250 0.2947
0.628 39.2857 3300 0.2940
0.632 39.8810 3350 0.2947
0.6259 40.4762 3400 0.2939
0.6305 41.0714 3450 0.2943
0.6381 41.6667 3500 0.2939
0.6341 42.2619 3550 0.2942
0.6163 42.8571 3600 0.2937
0.6256 43.4524 3650 0.2934
0.628 44.0476 3700 0.2934
0.6371 44.6429 3750 0.2945
0.6209 45.2381 3800 0.2930
0.6285 45.8333 3850 0.2939
0.6309 46.4286 3900 0.2938
0.6216 47.0238 3950 0.2935
0.6352 47.6190 4000 0.2943

Framework versions

  • Transformers 4.47.0.dev0
  • Pytorch 2.4.0
  • Datasets 3.0.1
  • Tokenizers 0.20.0
Downloads last month
21
Safetensors
Model size
144M params
Tensor type
F32
·
Inference Examples
Text-to-Audio
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Hawoly18/speecht5_tts_wolof

Base model

microsoft/speecht5_tts
Finetuned
Moustapha91/speecht5_finetuned_wo_v1
Finetuned
(2)
this model

Evaluation results

Metadata error: specify a dataset to view leaderboard