Make Example Easier To Use

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

examples/offline_inference/qwen_2_5_omni/README.md

@@ -63,22 +63,30 @@ uv pip install -r requirements.txt
 ```
 
 ## Run examples (Qwen2.5-omni)
-Download dataset from seed_tts[https://drive.google.com/file/d/1GlSjVfSHkW3-leKKBlfrjuuTGqQ_xaLP/edit]. To get the prompt, you can:
+### Multiple Prompts
+Download dataset from [seed_tts](https://drive.google.com/file/d/1GlSjVfSHkW3-leKKBlfrjuuTGqQ_xaLP/edit). To get the prompt, you can:
 ```bash
 tar -xf <Your Download Path>/seedtts_testset.tar
 cp seedtts_testset/en/meta.lst examples/offline_inference/qwen_2_5_omni/meta.lst
 python3 examples/offline_inference/qwen_2_5_omni/extract_prompts.py \
   --input examples/offline_inference/qwen_2_5_omni/meta.lst \
   --output examples/offline_inference/qwen_2_5_omni/top100.txt \
-  --topk 100 \
-  --pt-output examples/offline_inference/qwen_2_5_omni/top100.pt
+  --topk 100
 ```
 Get into the example folder
 ```bash
 cd examples/offline_inference/qwen_2_5_omni
 ```
-Modify PYTHONPATH in run.sh as your path of vllm_omni. Then run.
+Modify PYTHONPATH in run_multiple_prompts.sh as your path of vllm_omni. Then run.
 ```bash
-bash run.sh
+bash run_multiple_prompts.sh
+```
+### Single Prompts
+Get into the example folder
+```bash
+cd examples/offline_inference/qwen_2_5_omni
+```
+Modify PYTHONPATH in run_single_prompt.sh as your path of vllm_omni. Then run.
+```bash
+bash run_single_prompt.sh
 ```
-The output audio is saved in ./output_audio

examples/offline_inference/qwen_2_5_omni/end2end.py

@@ -51,9 +51,6 @@ def parse_args():
     parser.add_argument(
         "--prompts", nargs="+", default=None, help="Input text prompts."
     )
-    parser.add_argument(
-        "--pt-prompts", type=str, default=None, help="Path to .pt file containing List[str] prompts (overrides --prompts when prompt_type=text)."
-    )
     parser.add_argument(
         "--voice-type", default="default", help="Voice type, e.g., m02, f030, default."
     )
@@ -146,6 +143,12 @@ def parse_args():
         default=False,
         help="Enable writing detailed statistics (default: disabled)",
     )
+    parser.add_argument(
+        "--txt-prompts",
+        type=str,
+        default=None,
+        help="Path to a .txt file with one prompt per line (preferred).",
+    )
     args = parser.parse_args()
     return args
 
@@ -153,20 +156,19 @@ def parse_args():
 def main():
     args = parse_args()
     model_name = args.model
-    # If pt-prompts provided and prompt_type is text, load and override args.prompts
     try:
-        if getattr(args, "pt_prompts", None) and args.prompt_type == "text":
-            loaded = torch.load(args.pt_prompts)
-            if not isinstance(loaded, list) or (len(loaded) > 0 and not isinstance(loaded[0], str)):
-                raise ValueError("--pt-prompts must point to a .pt containing List[str]")
-            args.prompts = loaded
-            print(f"[Info] Loaded {len(args.prompts)} prompts from {args.pt_prompts}")
+        # Preferred: load from txt file (one prompt per line)
+        if getattr(args, "txt_prompts", None) and args.prompt_type == "text":
+            with open(args.txt_prompts, "r", encoding="utf-8") as f:
+                lines = [ln.strip() for ln in f.readlines()]
+            args.prompts = [ln for ln in lines if ln != ""]
+            print(f"[Info] Loaded {len(args.prompts)} prompts from {args.txt_prompts}")
     except Exception as e:
-        print(f"[Error] Failed to load pt-prompts: {e}")
+        print(f"[Error] Failed to load prompts: {e}")
         raise
 
     if args.prompts is None:
-        raise ValueError("No prompts provided. Use --prompts ... or --pt-prompts <file.pt> (with --prompt_type text)")
+        raise ValueError("No prompts provided. Use --prompts ... or --txt-prompts <file.txt> (with --prompt_type text)")
     omni_llm = OmniLLM(
         model=model_name,
         log_stats=args.enable_stats,

examples/offline_inference/qwen_2_5_omni/extract_prompts.py

@@ -18,10 +18,9 @@ def extract_prompt(line: str) -> Optional[str]:
 
 def main() -> None:
     parser = argparse.ArgumentParser()
-    parser.add_argument("--input", "-i", required=True, help="输入 .lst 文件路径")
-    parser.add_argument("--output", "-o", required=True, help="输出文件路径")
-    parser.add_argument("--topk", "-k", type=int, default=100, help="提取前 K 个 prompt（默认 100）")
-    parser.add_argument("--pt-output", "-p", type=str, default=None, help="可选：输出 .pt 文件路径（默认与 --output 同名 .pt）")
+    parser.add_argument("--input", "-i", required=True, help="Input .lst file path")
+    parser.add_argument("--output", "-o", required=True, help="Output file path")
+    parser.add_argument("--topk", "-k", type=int, default=100, help="Extract the top K prompts (default: 100)")
     args = parser.parse_args()
 
     prompts = []
@@ -37,10 +36,6 @@ def main() -> None:
         for p in prompts:
             f.write(p + "\n")
 
-    # 另存为 PyTorch 序列化的 .pt，内容为字符串列表
-    pt_path = args.pt_output if args.pt_output else os.path.splitext(args.output)[0] + ".pt"
-    torch.save(prompts, pt_path)
-
 
 if __name__ == "__main__":
     main()

examples/offline_inference/qwen_2_5_omni/run_multiple_prompts.sh

@@ -6,4 +6,4 @@ python end2end.py --model Qwen/Qwen2.5-Omni-7B \
                                  --output-wav output_audio \
                                  --prompt_type text \
                                  --init-sleep-seconds 0 \
-                                 --pt-prompts <Your_Prompt_File>.pt
+                                 --txt-prompts top100.txt

examples/offline_inference/qwen_2_5_omni/run_single_prompt.sh

@@ -0,0 +1,9 @@
+export PYTHONPATH=/path/to/vllm-omni:$PYTHONPATH
+python end2end.py --model Qwen/Qwen2.5-Omni-7B \
+                                 --voice-type "m02" \
+                                 --dit-ckpt none \
+                                 --bigvgan-ckpt none \
+                                 --output-wav output_audio \
+                                 --prompt_type text \
+                                 --init-sleep-seconds 0 \
+                                 --prompts "Explain the system architecture for a scalable audio generation pipeline. Answer in 15 words."