PiperTTS-IT / README.md
qaihm-bot's picture
v0.58.0
fef1848 verified
|
Raw
History Blame Contribute Delete
15.2 kB
metadata
library_name: pytorch
license: other
tags:
  - real_time
  - android
pipeline_tag: text-to-audio

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® X2 Elite QAIRT 2.45 Download
VOICE_AI float Snapdragon® X Elite QAIRT 2.45 Download
VOICE_AI float Snapdragon® 8 Gen 3 Mobile QAIRT 2.45 Download
VOICE_AI float Snapdragon® 8 Gen 1 Mobile QAIRT 2.45 Download
VOICE_AI float Qualcomm® QCS8275 QAIRT 2.45 Download
VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45 Download
VOICE_AI float Qualcomm® SA8775P QAIRT 2.45 Download
VOICE_AI float Snapdragon® 8 Elite Mobile QAIRT 2.45 Download
VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 Download
VOICE_AI float Qualcomm® SA7255P QAIRT 2.45 Download
VOICE_AI float Qualcomm® SA8295P QAIRT 2.45 Download
VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45 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:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
charsiu_decoder VOICE_AI float Snapdragon® X2 Elite 0.323 ms 1 - 1 MB NPU
charsiu_decoder VOICE_AI float Snapdragon® X Elite 0.426 ms 1 - 1 MB NPU
charsiu_decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 0.312 ms 0 - 7 MB NPU
charsiu_decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 0.578 ms 1 - 11 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® QCS8275 1.015 ms 0 - 9 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.4 ms 0 - 2 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® SA8775P 0.654 ms 0 - 10 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® SA8650P 0.654 ms 0 - 10 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® SA8255P 0.654 ms 0 - 10 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® QCS8450 0.578 ms 1 - 11 MB NPU
charsiu_decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 0.266 ms 0 - 10 MB NPU
charsiu_decoder VOICE_AI float Snapdragon® 8 Elite Mobile 0.276 ms 0 - 9 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® SA7255P 1.015 ms 0 - 9 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 0.519 ms 1 - 3 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® SA8295P 0.807 ms 0 - 6 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 0.276 ms 0 - 9 MB NPU
charsiu_decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 0.426 ms 1 - 1 MB NPU
charsiu_encoder VOICE_AI float Snapdragon® X2 Elite 0.63 ms 0 - 0 MB NPU
charsiu_encoder VOICE_AI float Snapdragon® X Elite 1.045 ms 0 - 0 MB NPU
charsiu_encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 0.637 ms 0 - 7 MB NPU
charsiu_encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 1.35 ms 0 - 9 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® QCS8275 2.802 ms 0 - 9 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.895 ms 0 - 1 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® SA8775P 1.26 ms 0 - 10 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® SA8650P 1.26 ms 0 - 10 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® SA8255P 1.26 ms 0 - 10 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® QCS8450 1.35 ms 0 - 9 MB NPU
charsiu_encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 0.488 ms 0 - 8 MB NPU
charsiu_encoder VOICE_AI float Snapdragon® 8 Elite Mobile 0.528 ms 0 - 9 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® SA7255P 2.802 ms 0 - 9 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 1.12 ms 0 - 2 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® SA8295P 1.742 ms 0 - 6 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 0.528 ms 0 - 9 MB NPU
charsiu_encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 1.045 ms 0 - 0 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 1.754 ms 0 - 0 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 3.081 ms 0 - 0 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 2.183 ms 0 - 7 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 4.362 ms 0 - 9 MB NPU
decoder VOICE_AI float Qualcomm® QCS8275 8.079 ms 0 - 9 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.023 ms 0 - 1 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 3.476 ms 0 - 5 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 3.476 ms 0 - 5 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 3.476 ms 0 - 5 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 4.362 ms 0 - 9 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 1.821 ms 0 - 9 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Mobile 1.892 ms 0 - 8 MB NPU
decoder VOICE_AI float Qualcomm® SA7255P 8.079 ms 0 - 9 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 3.336 ms 0 - 2 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 4.008 ms 0 - 5 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 1.892 ms 0 - 8 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 3.081 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 18.516 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 29.387 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 23.76 ms 0 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 39.427 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® QCS8275 47.257 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 30.367 ms 0 - 2 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 32.934 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 32.934 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 32.934 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 39.427 ms 0 - 10 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 17.08 ms 0 - 10 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Mobile 19.045 ms 0 - 13 MB NPU
encoder VOICE_AI float Qualcomm® SA7255P 47.257 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 32.982 ms 2 - 5 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 35.228 ms 0 - 6 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 19.045 ms 0 - 13 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 29.387 ms 0 - 0 MB NPU
flow VOICE_AI float Snapdragon® X2 Elite 9.738 ms 4 - 4 MB NPU
flow VOICE_AI float Snapdragon® X Elite 15.969 ms 4 - 4 MB NPU
flow VOICE_AI float Snapdragon® 8 Gen 3 Mobile 10.996 ms 4 - 11 MB NPU
flow VOICE_AI float Snapdragon® 8 Gen 1 Mobile 18.132 ms 3 - 12 MB NPU
flow VOICE_AI float Qualcomm® QCS8275 39.943 ms 1 - 10 MB NPU
flow VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 15.034 ms 4 - 5 MB NPU
flow VOICE_AI float Qualcomm® SA8775P 17.3 ms 1 - 11 MB NPU
flow VOICE_AI float Qualcomm® SA8650P 17.3 ms 1 - 11 MB NPU
flow VOICE_AI float Qualcomm® SA8255P 17.3 ms 1 - 11 MB NPU
flow VOICE_AI float Qualcomm® QCS8450 18.132 ms 3 - 12 MB NPU
flow VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 8.98 ms 2 - 10 MB NPU
flow VOICE_AI float Snapdragon® 8 Elite Mobile 8.816 ms 1 - 10 MB NPU
flow VOICE_AI float Qualcomm® SA7255P 39.943 ms 1 - 10 MB NPU
flow VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 17.389 ms 6 - 12 MB NPU
flow VOICE_AI float Qualcomm® SA8295P 18.832 ms 0 - 6 MB NPU
flow VOICE_AI float Qualcomm® Dragonwing™ Q-8750 8.816 ms 1 - 10 MB NPU
flow VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 15.969 ms 4 - 4 MB NPU
sdp VOICE_AI float Snapdragon® X2 Elite 7.135 ms 0 - 0 MB NPU
sdp VOICE_AI float Snapdragon® X Elite 11.237 ms 0 - 0 MB NPU
sdp VOICE_AI float Snapdragon® 8 Gen 3 Mobile 7.676 ms 0 - 8 MB NPU
sdp VOICE_AI float Snapdragon® 8 Gen 1 Mobile 11.186 ms 0 - 9 MB NPU
sdp VOICE_AI float Qualcomm® QCS8275 20.562 ms 0 - 9 MB NPU
sdp VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 10.361 ms 0 - 2 MB NPU
sdp VOICE_AI float Qualcomm® SA8775P 11.132 ms 0 - 10 MB NPU
sdp VOICE_AI float Qualcomm® SA8650P 11.132 ms 0 - 10 MB NPU
sdp VOICE_AI float Qualcomm® SA8255P 11.132 ms 0 - 10 MB NPU
sdp VOICE_AI float Qualcomm® QCS8450 11.186 ms 0 - 9 MB NPU
sdp VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 6.618 ms 0 - 8 MB NPU
sdp VOICE_AI float Snapdragon® 8 Elite Mobile 6.951 ms 0 - 13 MB NPU
sdp VOICE_AI float Qualcomm® SA7255P 20.562 ms 0 - 9 MB NPU
sdp VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 11.238 ms 0 - 2 MB NPU
sdp VOICE_AI float Qualcomm® SA8295P 12.674 ms 0 - 6 MB NPU
sdp VOICE_AI float Qualcomm® Dragonwing™ Q-8750 6.951 ms 0 - 13 MB NPU
sdp VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 11.237 ms 0 - 0 MB NPU

License

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

References

Community