Hugging Face's logo

qualcomm
/
PiperTTS-IT

Text-to-Audio
PyTorch
real_time
android
Model card Files
xet
 Community

PiperTTS-IT: Optimized for Qualcomm Devices

PiperTTS is a high-quality multi-lingual text-to-speech library.

This is based on the implementation of PiperTTS-IT found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® X2 Elite QAIRT 2.50 Download
VOICE_AI float Snapdragon® X Elite QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA8775P QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA7255P QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA8295P QAIRT 2.50 Download

For more device-specific assets and performance metrics, visit PiperTTS-IT on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

  • Custom weights (e.g., fine-tuned checkpoints)
  • Custom input shapes
  • Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for PiperTTS-IT on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.audio_generation

Model Stats:

  • Max decoded sequence length: 64 tokens
  • Model checkpoint: rhasspy/piper-voices
  • Model size (decoder) (float): 6.37 MB
  • Model size (encoder) (float): 28.7 MB
  • Model size (flow) (float): 28.2 MB
  • Model size (sdp) (float): 6.61 KB
  • Model size (t5_decoder) (float): 21.8 MB
  • Model size (t5_encoder) (float): 57.5 MB
  • Number of parameters (decoder): 1.66M
  • Number of parameters (encoder): 7.51M
  • Number of parameters (flow): 7.39M
  • Number of parameters (sdp): 1.04K
  • Number of parameters (t5_decoder): 5.72M
  • Number of parameters (t5_encoder): 15.1M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
charsiu_decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.265 ms 0 - 9 MB NPU
charsiu_decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 0.323 ms 0 - 8 MB NPU
charsiu_decoder VOICE_AI float Snapdragon® X2 Elite 0.355 ms 1 - 1 MB NPU
charsiu_decoder VOICE_AI float Snapdragon® X Elite 0.423 ms 1 - 1 MB NPU
charsiu_decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 0.306 ms 0 - 7 MB NPU
charsiu_decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 0.473 ms 1 - 11 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 0.584 ms 1 - 4 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.406 ms 0 - 2 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® SA8775P 0.67 ms 0 - 9 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® SA8650P 0.67 ms 0 - 9 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® SA8255P 0.67 ms 0 - 9 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® QCS8450 0.473 ms 1 - 11 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 0.531 ms 3 - 5 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 0.423 ms 1 - 1 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 0.323 ms 0 - 8 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® SA8295P 0.69 ms 0 - 5 MB NPU
charsiu_encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.491 ms 0 - 8 MB NPU
charsiu_encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 0.524 ms 0 - 8 MB NPU
charsiu_encoder VOICE_AI float Snapdragon® X2 Elite 0.647 ms 0 - 0 MB NPU
charsiu_encoder VOICE_AI float Snapdragon® X Elite 1.042 ms 0 - 0 MB NPU
charsiu_encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 0.627 ms 0 - 7 MB NPU
charsiu_encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 1.297 ms 0 - 10 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 1.08 ms 0 - 3 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.896 ms 0 - 1 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® SA8775P 1.224 ms 0 - 9 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® SA8650P 1.224 ms 0 - 9 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® SA8255P 1.224 ms 0 - 9 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® QCS8450 1.297 ms 0 - 10 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 1.121 ms 0 - 2 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 1.042 ms 0 - 0 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 0.524 ms 0 - 8 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® SA8295P 1.608 ms 0 - 5 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 4.467 ms 0 - 9 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 5.213 ms 0 - 9 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 4.191 ms 0 - 0 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 7.415 ms 1 - 1 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 6.026 ms 0 - 7 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 4.804 ms 0 - 10 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 7.941 ms 0 - 3 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.727 ms 0 - 2 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 7.927 ms 0 - 9 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 7.927 ms 0 - 9 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 7.927 ms 0 - 9 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 4.804 ms 0 - 10 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 7.64 ms 0 - 2 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 7.415 ms 1 - 1 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 5.213 ms 0 - 9 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 5.348 ms 0 - 5 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 8.865 ms 0 - 9 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 9.322 ms 0 - 8 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 8.378 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 15.674 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 10.906 ms 0 - 7 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 17.572 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 16.245 ms 0 - 4 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 15.855 ms 0 - 2 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 17.003 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 17.003 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 17.003 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 17.572 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 17.049 ms 0 - 3 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 15.674 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 9.322 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 19.921 ms 0 - 6 MB NPU
flow VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 9.17 ms 3 - 10 MB NPU
flow VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 8.436 ms 1 - 13 MB NPU
flow VOICE_AI float Snapdragon® X2 Elite 9.732 ms 4 - 4 MB NPU
flow VOICE_AI float Snapdragon® X Elite 15.102 ms 4 - 4 MB NPU
flow VOICE_AI float Snapdragon® 8 Gen 3 Mobile 10.76 ms 4 - 12 MB NPU
flow VOICE_AI float Snapdragon® 8 Gen 1 Mobile 16.629 ms 4 - 13 MB NPU
flow VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 17.081 ms 4 - 12 MB NPU
flow VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 14.331 ms 4 - 5 MB NPU
flow VOICE_AI float Qualcomm® SA8775P 16.409 ms 1 - 10 MB NPU
flow VOICE_AI float Qualcomm® SA8650P 16.409 ms 1 - 10 MB NPU
flow VOICE_AI float Qualcomm® SA8255P 16.409 ms 1 - 10 MB NPU
flow VOICE_AI float Qualcomm® QCS8450 16.629 ms 4 - 13 MB NPU
flow VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 16.57 ms 4 - 11 MB NPU
flow VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 15.102 ms 4 - 4 MB NPU
flow VOICE_AI float Qualcomm® Dragonwing™ Q-8750 8.436 ms 1 - 13 MB NPU
flow VOICE_AI float Qualcomm® SA8295P 18.062 ms 0 - 5 MB NPU
sdp VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 7.244 ms 0 - 8 MB NPU
sdp VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 7.437 ms 0 - 8 MB NPU
sdp VOICE_AI float Snapdragon® X2 Elite 7.759 ms 0 - 0 MB NPU
sdp VOICE_AI float Snapdragon® X Elite 12.088 ms 0 - 0 MB NPU
sdp VOICE_AI float Snapdragon® 8 Gen 3 Mobile 8.139 ms 0 - 8 MB NPU
sdp VOICE_AI float Snapdragon® 8 Gen 1 Mobile 11.898 ms 0 - 10 MB NPU
sdp VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 11.038 ms 0 - 4 MB NPU
sdp VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 11.262 ms 0 - 3 MB NPU
sdp VOICE_AI float Qualcomm® SA8775P 11.965 ms 0 - 10 MB NPU
sdp VOICE_AI float Qualcomm® SA8650P 11.965 ms 0 - 10 MB NPU
sdp VOICE_AI float Qualcomm® SA8255P 11.965 ms 0 - 10 MB NPU
sdp VOICE_AI float Qualcomm® QCS8450 11.898 ms 0 - 10 MB NPU
sdp VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 12.116 ms 0 - 3 MB NPU
sdp VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 12.088 ms 0 - 0 MB NPU
sdp VOICE_AI float Qualcomm® Dragonwing™ Q-8750 7.437 ms 0 - 8 MB NPU
sdp VOICE_AI float Qualcomm® SA8295P 13.425 ms 0 - 5 MB NPU

License

  • The license for the original implementation of PiperTTS-IT can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Text-to-Audio
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support