Hugging Face's logo

qualcomm
/
MeloTTS-KO

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

MeloTTS-KO: Optimized for Qualcomm Devices

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

This is based on the implementation of MeloTTS-KO 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-KO 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® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI mixed_with_float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI mixed_with_float Snapdragon® X2 Elite QAIRT 2.50 Download
VOICE_AI mixed_with_float Snapdragon® X Elite QAIRT 2.50 Download
VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50 Download
VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50 Download
VOICE_AI mixed_with_float Qualcomm® SA8775P QAIRT 2.50 Download
VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50 Download
VOICE_AI mixed_with_float Qualcomm® SA7255P QAIRT 2.50 Download
VOICE_AI mixed_with_float Snapdragon® 8 Elite Extreme Gen 6 Mobile QAIRT 2.50 Download
VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 6 Mobile QAIRT 2.50 Download

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

Model Details

Model Type: Model_use_case.audio_generation

Model Stats:

  • Max decoded sequence length: 512 tokens
  • Model checkpoint: myshell-ai/MeloTTS-Korean
  • Model size (bert_wrapper) (float): 581 MB
  • Model size (charsiu_decoder) (float): 21.8 MB
  • Model size (charsiu_encoder) (float): 57.5 MB
  • Model size (decoder) (float): 55.5 MB
  • Model size (encoder) (float): 30.5 MB
  • Model size (flow) (float): 76.9 MB
  • Model size (sdp) (float): 1.52 MB
  • Number of parameters (bert_wrapper): 152M
  • Number of parameters (charsiu_decoder): 5.72M
  • Number of parameters (charsiu_encoder): 15.1M
  • Number of parameters (decoder): 14.5M
  • Number of parameters (encoder): 7.97M
  • Number of parameters (flow): 20.1M
  • Number of parameters (sdp): 395K

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.686 ms 0 - 8 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Elite For Galaxy Mobile 3.223 ms 0 - 12 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® X2 Elite 2.915 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® X Elite 6.177 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 5.637 ms 0 - 4 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.932 ms 0 - 2 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 5.756 ms 0 - 3 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 6.177 ms 0 - 0 MB NPU
bert_wrapper VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 3.223 ms 0 - 12 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Elite Extreme Gen 6 Mobile 2.413 ms 0 - 10 MB NPU
bert_wrapper VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 6 Mobile 2.923 ms 0 - 9 MB NPU
charsiu_decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.284 ms 0 - 8 MB NPU
charsiu_decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite For Galaxy Mobile 0.282 ms 0 - 12 MB NPU
charsiu_decoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 0.313 ms 1 - 1 MB NPU
charsiu_decoder VOICE_AI mixed_with_float Snapdragon® X Elite 0.421 ms 1 - 1 MB NPU
charsiu_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 0.584 ms 1 - 4 MB NPU
charsiu_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.409 ms 0 - 2 MB NPU
charsiu_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 0.53 ms 3 - 5 MB NPU
charsiu_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 0.421 ms 1 - 1 MB NPU
charsiu_decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 0.282 ms 0 - 12 MB NPU
charsiu_decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.251 ms 0 - 10 MB NPU
charsiu_decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 6 Mobile 0.263 ms 0 - 10 MB NPU
charsiu_encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.488 ms 0 - 9 MB NPU
charsiu_encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite For Galaxy Mobile 0.525 ms 0 - 12 MB NPU
charsiu_encoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 0.666 ms 0 - 0 MB NPU
charsiu_encoder VOICE_AI mixed_with_float Snapdragon® X Elite 1.072 ms 0 - 0 MB NPU
charsiu_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 1.075 ms 0 - 3 MB NPU
charsiu_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.88 ms 0 - 1 MB NPU
charsiu_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 1.119 ms 2 - 4 MB NPU
charsiu_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 1.072 ms 0 - 0 MB NPU
charsiu_encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 0.525 ms 0 - 12 MB NPU
charsiu_encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.438 ms 0 - 10 MB NPU
charsiu_encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 6 Mobile 0.444 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 15.907 ms 0 - 7 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite For Galaxy Mobile 17.714 ms 0 - 8 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 14.396 ms 0 - 0 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® X Elite 28.322 ms 1 - 1 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 32.261 ms 0 - 3 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 28.812 ms 0 - 2 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 31.194 ms 0 - 2 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 28.322 ms 1 - 1 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 17.714 ms 0 - 8 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Extreme Gen 6 Mobile 10.768 ms 0 - 10 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 6 Mobile 15.351 ms 0 - 10 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 10.819 ms 2 - 9 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite For Galaxy Mobile 10.969 ms 2 - 14 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 10.124 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® X Elite 18.147 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 18.848 ms 4 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 18.199 ms 4 - 5 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 19.539 ms 4 - 10 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 18.147 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 10.969 ms 2 - 14 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Extreme Gen 6 Mobile 6.246 ms 4 - 13 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 6 Mobile 10.622 ms 4 - 13 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 32.158 ms 3 - 12 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite For Galaxy Mobile 42.549 ms 3 - 16 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® X2 Elite 32.315 ms 4 - 4 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® X Elite 75.502 ms 4 - 4 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 69.734 ms 4 - 12 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 73.949 ms 5 - 6 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 73.353 ms 4 - 11 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 75.502 ms 4 - 4 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 42.549 ms 3 - 16 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite Extreme Gen 6 Mobile 25.587 ms 4 - 13 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 6 Mobile 37.62 ms 4 - 13 MB NPU
sdp VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.404 ms 0 - 9 MB NPU
sdp VOICE_AI mixed_with_float Snapdragon® 8 Elite For Galaxy Mobile 0.441 ms 0 - 8 MB NPU
sdp VOICE_AI mixed_with_float Snapdragon® X2 Elite 0.514 ms 0 - 0 MB NPU
sdp VOICE_AI mixed_with_float Snapdragon® X Elite 0.888 ms 0 - 0 MB NPU
sdp VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-8275 0.783 ms 0 - 4 MB NPU
sdp VOICE_AI mixed_with_float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.741 ms 0 - 2 MB NPU
sdp VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-9075 0.862 ms 0 - 3 MB NPU
sdp VOICE_AI mixed_with_float Qualcomm® Dragonwing™ IQ-X7181 0.888 ms 0 - 0 MB NPU
sdp VOICE_AI mixed_with_float Qualcomm® Dragonwing™ Q-8750 0.441 ms 0 - 8 MB NPU
sdp VOICE_AI mixed_with_float Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.344 ms 0 - 10 MB NPU
sdp VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 6 Mobile 0.4 ms 0 - 10 MB NPU

License

  • The license for the original implementation of MeloTTS-KO 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