add ct_tn.py (#2795)

Co-authored-by: 启焚 <[email protected]>

examples/industrial_data_pretraining/fun_asr_nano/tools/format5res.py

@@ -155,9 +155,7 @@ def ch_number2digit(line):
         if line[i] in chsh:
             number_flag = 1
             if line[i] == "两":
-                if (i == len(line) - 1) or (
-                    (line[i + 1] not in chsh.keys()) and (line[i + 1] not in bits.keys())
-                ):
+                if (i == len(line) - 1) or ((line[i + 1] not in chsh.keys()) and (line[i + 1] not in bits.keys())):
                     number_flag = -1
             if number_flag == 1:
                 digit.append(chsh[line[i]])

examples/industrial_data_pretraining/fun_asr_nano/tools/scp2jsonl.py

@@ -86,9 +86,7 @@ def main_hydra(cfg: DictConfig):
         transcript_lines = f2.readlines()
 
     if len(scp_lines) != len(transcript_lines):
-        print(
-            f"Warning: Line count mismatch - scp: {len(scp_lines)}, transcript: {len(transcript_lines)}"
-        )
+        print(f"Warning: Line count mismatch - scp: {len(scp_lines)}, transcript: {len(transcript_lines)}")
 
     tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-0.6B")
     processor = LineProcessor(tokenizer)
@@ -102,10 +100,7 @@ def main_hydra(cfg: DictConfig):
     with tqdm(total=len(data_pairs), desc="Processing") as pbar:
         with ThreadPoolExecutor(max_workers=max_workers) as executor:
             with open(jsonl_file, "w") as f_out:
-                futures = {
-                    executor.submit(processor.process_line, pair): i
-                    for i, pair in enumerate(data_pairs)
-                }
+                futures = {executor.submit(processor.process_line, pair): i for i, pair in enumerate(data_pairs)}
 
                 for future in as_completed(futures):
                     result = future.result()