Hugging Face's logo

qualcomm
/
MeloTTS-ES

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

MeloTTS-ES: 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-ES 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-ES 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® 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® QCS9075 QAIRT 2.45 Download

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

Model Details

Model Type: Model_use_case.audio_generation

Model Stats:

  • Model checkpoint: myshell-ai/MeloTTS-Spanish
  • Max decoded sequence length: 512 tokens
  • Number of parameters (encoder): 8.36M
  • Model size (encoder) (float): 32.0 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 (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
decoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 41.011 ms 1 - 1 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® X Elite 82.765 ms 1 - 1 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 61.274 ms 0 - 7 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® QCS8275 134.7 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® QCS8550 (Proxy) 85.042 ms 0 - 2 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® QCS9075 83.334 ms 0 - 2 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® SA7255P 134.7 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 48.522 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 42.332 ms 0 - 8 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® QCS8750 48.522 ms 0 - 9 MB NPU
decoder VOICE_AI mixed_with_float Qualcomm® QCS7181 82.765 ms 1 - 1 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 25.239 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® X Elite 40.319 ms 4 - 4 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 30.796 ms 9 - 16 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® QCS8275 66.231 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® QCS8550 (Proxy) 40.719 ms 4 - 5 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® QCS9075 43.288 ms 4 - 9 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® SA7255P 66.231 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 25.37 ms 2 - 14 MB NPU
encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 23.803 ms 2 - 11 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® QCS8750 25.37 ms 2 - 14 MB NPU
encoder VOICE_AI mixed_with_float Qualcomm® QCS7181 40.319 ms 4 - 4 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® X2 Elite 67.36 ms 2 - 2 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® X Elite 129.18 ms 2 - 2 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 99.328 ms 4 - 12 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® QCS8275 245.474 ms 2 - 10 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® QCS8550 (Proxy) 131.803 ms 2 - 3 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® QCS9075 127.929 ms 2 - 6 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® SA7255P 245.474 ms 2 - 10 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 81.776 ms 2 - 15 MB NPU
flow VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 71.151 ms 2 - 10 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® QCS8750 81.776 ms 2 - 15 MB NPU
flow VOICE_AI mixed_with_float Qualcomm® QCS7181 129.18 ms 2 - 2 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 0.326 ms 1 - 1 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® X Elite 0.443 ms 1 - 1 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 0.312 ms 0 - 7 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® QCS8275 0.975 ms 0 - 8 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® QCS8550 (Proxy) 0.404 ms 1 - 2 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® QCS9075 0.519 ms 1 - 3 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® SA7255P 0.975 ms 0 - 8 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 0.285 ms 0 - 9 MB NPU
t5_decoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 0.262 ms 0 - 9 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® QCS8750 0.285 ms 0 - 9 MB NPU
t5_decoder VOICE_AI mixed_with_float Qualcomm® QCS7181 0.443 ms 1 - 1 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® X2 Elite 0.64 ms 0 - 0 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® X Elite 1.042 ms 0 - 0 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® 8 Gen 3 Mobile 0.638 ms 0 - 8 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® QCS8275 2.803 ms 0 - 8 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® QCS8550 (Proxy) 0.886 ms 0 - 1 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® QCS9075 1.136 ms 0 - 2 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® SA7255P 2.803 ms 0 - 8 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Mobile 0.524 ms 0 - 9 MB NPU
t5_encoder VOICE_AI mixed_with_float Snapdragon® 8 Elite Gen 5 Mobile 0.49 ms 0 - 8 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® QCS8750 0.524 ms 0 - 9 MB NPU
t5_encoder VOICE_AI mixed_with_float Qualcomm® QCS7181 1.042 ms 0 - 0 MB NPU

License

  • The license for the original implementation of MeloTTS-ES 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