Update app.py

app.py

@@ -17,12 +17,12 @@ YT_LENGTH_LIMIT_S = 4800  # 1 hour limit
 device = 0 if torch.cuda.is_available() else "cpu"
 pipe = pipeline(task="automatic-speech-recognition", model=MODEL_NAME, chunk_length_s=30, device=device)
 
-JSON_DATASET_DIR = Path("youtube-transcripts")
+JSON_DATASET_DIR = Path("json_dataset")
 JSON_DATASET_DIR.mkdir(parents=True, exist_ok=True)
 JSON_DATASET_PATH = JSON_DATASET_DIR / f"transcriptions-{uuid4()}.json"
 
 scheduler = CommitScheduler(
-    repo_id="your-dataset-repo",
+    repo_id="transcript-dataset",
     repo_type="dataset",
     folder_path=JSON_DATASET_DIR,
     path_in_repo="data",