Upload quantized checkpoint via upload_hf.sh

README.md

@@ -75,7 +75,7 @@ BF16 baseline WER: 7.34% (measured on x86; not runnable on Nano due to memory).
 
 This checkpoint is the **input to the TRT-EdgeLLM export pipeline**.
 It is **not** directly loadable by standard `transformers` inference —
-use it with [qwen3-asr-optimization](https://github.com/VLAOpt/qwen3-asr-optimization)
+use it with [qwen-asr-optimization](https://github.com/VLAOpt/qwen-asr-optimization)
 to export to ONNX and build TRT engines.
 
 ```
@@ -109,13 +109,13 @@ to export to ONNX and build TRT engines.
 ## Deployment
 
 Full pipeline documentation:
-[trt-edgellm/README.md](https://github.com/VLAOpt/qwen3-asr-optimization/blob/main/trt-edgellm/README.md)
+[trt-edgellm/README.md](https://github.com/VLAOpt/qwen-asr-optimization/blob/main/trt-edgellm/README.md)
 
 ### Quick start
 
 ```bash
-git clone https://github.com/VLAOpt/qwen3-asr-optimization.git
-cd qwen3-asr-optimization
+git clone https://github.com/VLAOpt/qwen-asr-optimization.git
+cd qwen-asr-optimization
 
 # Download this checkpoint
 huggingface-cli download vrfai/qwen3asr-int4 --local-dir ./Qwen3-ASR-1.7B-int4
@@ -152,4 +152,4 @@ python trt-edgellm/inference.py \
 - [Qwen3-ASR Technical Report](https://arxiv.org/abs/2601.21337)
 - [NVIDIA ModelOpt](https://nvidia.github.io/TensorRT-Model-Optimizer/)
 - [TensorRT-Edge-LLM v0.6.0](https://nvidia.github.io/TensorRT-Edge-LLM/0.6.0/)
-- [qwen3-asr-optimization repo](https://github.com/VLAOpt/qwen3-asr-optimization)
+- [qwen-asr-optimization repo](https://github.com/VLAOpt/qwen-asr-optimization)