Update README.md

README.md

@@ -16,42 +16,75 @@ base_model:
 pipeline_tag: text-to-speech
 ---
 
-# IndicF5-TTS Tensorrt-LLM Fast Inference - Zuppppppp
+# IndicF5-TTS TensorRT-LLM Fast Inference – Zuppppppp 🚀
 
-Accelerate inference for Indic-F5 TTS. Will be sharing benchmarks soon, 
-would be cool if someone else can compare and put it up earlier though.
+Fast inference version of IndicF5 TTS using TensorRT-LLM. Supports 11 Indian languages.
 
-Received so many queries and requests for a faster model. We heard you, sharing with ❤️ from Saryps Labs.
+---
+
+Accelerated inference for IndicF5 TTS – made for those of you who asked for speed! We heard you loud and clear. Sharing with ❤️ from **Saryps Labs**.
+
+This build is based on the amazing work at [wgs/F5-TTS-Faster](https://huggingface.co/wgs/F5-TTS-Faster), which converts F5-TTS checkpoints to run with TensorRT-LLM.
+
+### 🔧 How it works (a quick overview)
+Here’s the basic workflow used for acceleration (as shared in [wgs/F5-TTS-Faster](https://huggingface.co/wgs/F5-TTS-Faster)):
+
+- First, export **F5-TTS** to ONNX in three parts.
+- Then, use **TensorRT-LLM** to rewrite the relevant **Transformer** parts of the network for acceleration.
+- The front-end and decoder still use ONNX inference.  
+- You can also use `CUDAExecutionProvider`, `OpenVINOExecutionProvider`, etc., depending on your setup.
 
-Used the lovely work done here - https://huggingface.co/wgs/F5-TTS-Faster to convert checkpoints to trtllm.
-Sharing an excerpt from the repo here (https://huggingface.co/wgs/F5-TTS-Faster)
-The entire project workflow can be summarized as follows:
+If you're curious about the details, dive into the [original repo](https://github.com/WGS-note/F5_TTS_Faster) or ping me — happy to expand on anything.
 
-- First F5-TTSexport ONNXit into three parts;
-- Then use to rewrite Tensorrt-LLMthe relevant Transformerparts of the network for acceleration.
-  The front end and decode still use ONNXinference. Of course, you can also specify CUDAExecutionProvider, OpenVINOExecutionProvideretc.
+---
+
+### 🚀 Quickstart
+
+To try it out yourself:
 
-Kinda gives an overview of how it works. Feel free to spend sometime over the OG repo for more info or let me know if
-I can expand on anything.
+1. Clone the [F5_TTS_Faster](https://github.com/WGS-note/F5_TTS_Faster) repo.
+2. Set up the environment for TensorRT-LLM models (follow the repo instructions – it’s a little convoluted, but manageable).
+3. Place the `ckpts` folder at the root of the project.
+4. Run the sample script inside `export_trtllm/` to begin inference.
 
-For usage and details(conversion and inference): https://github.com/WGS-note/F5_TTS_Faster
-```
-- Clone the repo.
-- Setup environment for tensorrt-llm models to run. (Follow the repo instructions, a little convoluted.)
-- Place the ckpts folder at the root location.
-- Run the sample file inside export_trtllm.
-```
+Benchmarks coming soon! If you try it out and get some numbers, would be awesome if you can share back 🫡
+
+---
 
-Special thanks to below works and their awesome authors:
+### 🗣️ Supported Languages
+
+This model supports high-quality TTS synthesis in the following Indian languages:
+
+- Hindi (`hi`)
+- Telugu (`te`)
+- Assamese (`as`)
+- Bengali (`bn`)
+- Gujarati (`gu`)
+- Marathi (`mr`)
+- Kannada (`kn`)
+- Malayalam (`ml`)
+- Odia (`or`)
+- Punjabi (`pa`)
+- Tamil (`ta`)
+
+---
+
+### 🙏 Credits
+
+Massive thanks to the original authors and repositories that made this possible:
+
+- https://huggingface.co/ai4bharat/IndicF5  
+- https://huggingface.co/wgs/F5-TTS-Faster  
+- https://github.com/DakeQQ/F5-TTS-ONNX  
+- https://github.com/SWivid/F5-TTS  
+
+---
 
-- https://huggingface.co/ai4bharat/IndicF5
-- https://huggingface.co/wgs/F5-TTS-Faster
-- https://github.com/DakeQQ/F5-TTS-ONNX
-- https://github.com/SWivid/F5-TTS
+### 📜 Terms of Use
 
-**Terms of Use**
+By using this model, you agree to only clone voices for which you have **explicit permission**.  
+Unauthorized voice cloning is **strictly prohibited**. Any misuse of this model is the **sole responsibility of the user**.
 
-By using this model, you agree to only clone voices for which you have explicit permission. 
-Unauthorized voice cloning is strictly prohibited. Any misuse of this model is the responsibility of the user.
+Please don’t misuse this. Let’s build cool stuff, not cause trouble.
 
-Don't misuse or cause any trouble people.
+---