Update README.md
Browse files
README.md
CHANGED
|
@@ -12,11 +12,13 @@ tags:
|
|
| 12 |
pipeline_tag: text-to-speech
|
| 13 |
---
|
| 14 |
|
| 15 |
-
# Supertonic TTS Quantization for
|
| 16 |
|
| 17 |
A step-by-step guide to quantize the [Supertonic TTS](https://huggingface.co/Supertone/supertonic) model for Qualcomm QCS6490 using QAIRT/QNN.
|
| 18 |
Note: To achieve the optimal performance and accuracy consider generating ctx binaries or serialised binaries specific to the architecture (v68 - mine)
|
| 19 |
|
|
|
|
|
|
|
| 20 |
## Sample Output
|
| 21 |
|
| 22 |
Audio generated on QCS6490 board using quantized models (10 diffusion steps, raw and noisy):
|
|
|
|
| 12 |
pipeline_tag: text-to-speech
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# Supertonic TTS Quantization for Quakcomm chipsets
|
| 16 |
|
| 17 |
A step-by-step guide to quantize the [Supertonic TTS](https://huggingface.co/Supertone/supertonic) model for Qualcomm QCS6490 using QAIRT/QNN.
|
| 18 |
Note: To achieve the optimal performance and accuracy consider generating ctx binaries or serialised binaries specific to the architecture (v68 - mine)
|
| 19 |
|
| 20 |
+
### I would be using QCS6490 chip architecture for walking through the steps.
|
| 21 |
+
|
| 22 |
## Sample Output
|
| 23 |
|
| 24 |
Audio generated on QCS6490 board using quantized models (10 diffusion steps, raw and noisy):
|