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® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® SA8775P QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45 Download
VOICE_AI mixed_with_float Qualcomm® SA7255P 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

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 3.258 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® X Elite 7.705 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 5.028 ms 0 - 8 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8275 30.638 ms 0 - 10 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.088 ms 0 - 2 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA8775P 9.268 ms 0 - 10 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA8650P 9.268 ms 0 - 10 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA8255P 9.268 ms 0 - 10 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 9.028 ms 0 - 2 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 7.705 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 3.32 ms 0 - 9 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® SA7255P 30.638 ms 0 - 10 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 3.32 ms 0 - 9 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 2.691 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 41.382 ms 1 - 1 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® X Elite 82.62 ms 1 - 1 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 60.914 ms 0 - 8 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8275 134.968 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 84.658 ms 1 - 2 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA8775P 83.784 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA8650P 83.784 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA8255P 83.784 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 82.746 ms 0 - 2 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 82.62 ms 1 - 1 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 48.152 ms 0 - 13 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA7255P 134.968 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 48.152 ms 0 - 13 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 42.419 ms 0 - 8 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 25.331 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® X Elite 40.349 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 30.104 ms 4 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8275 66.529 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 40.686 ms 4 - 5 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA8775P 43.34 ms 1 - 7 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA8650P 43.34 ms 1 - 7 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA8255P 43.34 ms 1 - 7 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 42.825 ms 4 - 9 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 40.349 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 24.707 ms 2 - 10 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA7255P 66.529 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 24.707 ms 2 - 10 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 23.839 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® X2 Elite 67.589 ms 2 - 2 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® X Elite 129.768 ms 2 - 2 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 98.178 ms 2 - 10 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8275 245.488 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 131.12 ms 3 - 4 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA8775P 128.654 ms 2 - 12 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA8650P 128.654 ms 2 - 12 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA8255P 128.654 ms 2 - 12 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 127.408 ms 1 - 5 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 129.768 ms 2 - 2 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 82.501 ms 2 - 12 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA7255P 245.488 ms 2 - 11 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 82.501 ms 2 - 12 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 71.147 ms 2 - 11 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 0.308 ms 1 - 1 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® X Elite 0.436 ms 1 - 1 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 0.301 ms 0 - 7 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8275 0.988 ms 0 - 9 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.421 ms 0 - 2 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® SA8775P 0.661 ms 0 - 10 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® SA8650P 0.661 ms 0 - 10 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® SA8255P 0.661 ms 0 - 10 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 0.518 ms 1 - 3 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 0.436 ms 1 - 1 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 0.297 ms 0 - 13 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® SA7255P 0.988 ms 0 - 9 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 0.297 ms 0 - 13 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 0.26 ms 0 - 9 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 0.623 ms 0 - 0 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® X Elite 1.06 ms 0 - 0 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 0.634 ms 0 - 8 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8275 2.772 ms 0 - 8 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.898 ms 0 - 1 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® SA8775P 1.265 ms 0 - 10 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® SA8650P 1.265 ms 0 - 10 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® SA8255P 1.265 ms 0 - 10 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 1.4 ms 2 - 4 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 1.06 ms 0 - 0 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 0.521 ms 0 - 9 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® SA7255P 2.772 ms 0 - 8 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 0.521 ms 0 - 9 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 0.486 ms 0 - 9 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
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support