add data download instructions
Signed-off-by: tzhouam <tzhouam@connect.ust.hk> Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
This commit is contained in:
1 parent
7b9fa7708a
commit
c10cbbd2ea
3 files changed
+58
-1
No files matched your search
@@ -63,7 +63,16 @@ uv pip install -r requirements.txt
|
|||||||
```
|
```
|
||||||
|
|
||||||
## Run examples (Qwen2.5-omni)
|
## 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:
|
||||||
|
```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
|
||||||
|
```
|
||||||
Get into the example folder
|
Get into the example folder
|
||||||
```bash
|
```bash
|
||||||
cd examples/offline_inference/qwen_2_5_omni
|
cd examples/offline_inference/qwen_2_5_omni
|
||||||
|
|||||||
@@ -0,0 +1,48 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
import argparse
|
||||||
|
from typing import Optional
|
||||||
|
import os
|
||||||
|
import torch
|
||||||
|
|
||||||
|
|
||||||
|
def extract_prompt(line: str) -> Optional[str]:
|
||||||
|
# 提取第一个 '|' 与第二个 '|' 之间的内容
|
||||||
|
i = line.find('|')
|
||||||
|
if i == -1:
|
||||||
|
return None
|
||||||
|
j = line.find('|', i + 1)
|
||||||
|
if j == -1:
|
||||||
|
return None
|
||||||
|
return line[i + 1:j].strip()
|
||||||
|
|
||||||
|
|
||||||
|
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)")
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
prompts = []
|
||||||
|
with open(args.input, "r", encoding="utf-8", errors="ignore") as f:
|
||||||
|
for line in f:
|
||||||
|
if len(prompts) >= args.topk:
|
||||||
|
break
|
||||||
|
p = extract_prompt(line.rstrip("\n"))
|
||||||
|
if p:
|
||||||
|
prompts.append(p)
|
||||||
|
|
||||||
|
with open(args.output, "w", encoding="utf-8") as f:
|
||||||
|
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()
|
||||||
|
|
||||||
|
|
||||||
Binary file not shown.
Reference in new issue
Block a user