Hugging Face's logo

qualcomm
/
MeloTTS-EN

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

MeloTTS-EN: Optimized for Qualcomm Devices

MeloTTS is a high-quality multi-lingual text-to-speech library for English, Chinese and Spanish language.

This is based on the implementation of MeloTTS-EN 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.

Deploying MeloTTS-EN on-device

This model is compatible with the Qualcomm Voice AI SDK. Download the SDK from the Qualcomm Package Manager to deploy this model on-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 mixed_with_float Snapdragon® X2 Elite QAIRT 2.45 Download
VOICE_AI mixed_with_float Snapdragon® X Elite QAIRT 2.45 Download
VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® QCS8275 QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® SA8775P QAIRT 2.45 Download
VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile QAIRT 2.45 Download
VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® SA7255P QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit MeloTTS-EN 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 MeloTTS-EN on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.audio_generation

Model Stats:

  • Model checkpoint: myshell-ai/MeloTTS-English
  • Max decoded sequence length: 512 tokens
  • Number of parameters (encoder): 8.30M
  • Model size (encoder) (float): 31.8 MB
  • Number of parameters (flow): 20.1M
  • Model size (flow) (float): 76.9 MB
  • Number of parameters (decoder): 14.5M
  • Model size (decoder) (float): 55.5 MB
  • Number of parameters (bert_wrapper): 94.5M
  • Model size (bert_wrapper) (float): 360 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
bert_wrapper VOICE_AI mixed_with_float Snapdragon® X2 Elite 3.279 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® X Elite 7.725 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 5.034 ms 0 - 8 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® QCS8275 30.632 ms 0 - 8 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.083 ms 0 - 2 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA8775P 9.316 ms 0 - 9 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA8650P 9.316 ms 0 - 9 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA8255P 9.316 ms 0 - 9 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 10.422 ms 2 - 4 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 2.686 ms 0 - 9 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA7255P 30.632 ms 0 - 8 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 3.327 ms 0 - 9 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 3.327 ms 0 - 9 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 7.725 ms 0 - 0 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 40.825 ms 0 - 0 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® X Elite 82.775 ms 1 - 1 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 60.788 ms 0 - 8 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® QCS8275 134.493 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 85.343 ms 1 - 2 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA8775P 83.827 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA8650P 83.827 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA8255P 83.827 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 83.517 ms 0 - 2 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 42.432 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA7255P 134.493 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 47.971 ms 0 - 13 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 47.971 ms 0 - 13 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 82.775 ms 1 - 1 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 25.742 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® X Elite 39.999 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 30.206 ms 4 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® QCS8275 66.041 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 40.537 ms 4 - 6 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA8775P 43.143 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA8650P 43.143 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA8255P 43.143 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 43.869 ms 4 - 9 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 23.871 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA7255P 66.041 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 25.411 ms 2 - 15 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 25.411 ms 2 - 15 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 39.999 ms 4 - 4 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® X2 Elite 67.219 ms 2 - 2 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® X Elite 129.112 ms 2 - 2 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 98.085 ms 2 - 10 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® QCS8275 245.603 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 131.492 ms 2 - 4 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA8775P 128.536 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA8650P 128.536 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA8255P 128.536 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 127.556 ms 2 - 6 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 71.075 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA7255P 245.603 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 82.176 ms 2 - 15 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 82.176 ms 2 - 15 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 129.112 ms 2 - 2 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 0.374 ms 1 - 1 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® X Elite 0.42 ms 1 - 1 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 0.302 ms 0 - 8 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® QCS8275 0.995 ms 0 - 8 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.4 ms 0 - 2 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® SA8775P 0.645 ms 0 - 9 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® SA8650P 0.645 ms 0 - 9 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® SA8255P 0.645 ms 0 - 9 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 0.51 ms 1 - 3 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 0.259 ms 0 - 9 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® SA7255P 0.995 ms 0 - 8 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 0.305 ms 0 - 9 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 0.305 ms 0 - 9 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 0.42 ms 1 - 1 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 0.63 ms 0 - 0 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® X Elite 1.076 ms 0 - 0 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 0.636 ms 0 - 7 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® QCS8275 2.795 ms 0 - 9 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.896 ms 0 - 1 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® SA8775P 1.257 ms 0 - 10 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® SA8650P 1.257 ms 0 - 10 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® SA8255P 1.257 ms 0 - 10 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 1.121 ms 0 - 2 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 0.486 ms 0 - 9 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® SA7255P 2.795 ms 0 - 9 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 0.522 ms 0 - 9 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 0.522 ms 0 - 9 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 1.076 ms 0 - 0 MB NPU

License

  • The license for the original implementation of MeloTTS-EN 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