Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -19,6 +19,16 @@ def load_huggingface_dataset(dataset_link, token):
|
|
| 19 |
# print(df)
|
| 20 |
return df[["index", "transcription"]], dataset
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
def update_transcriptions(df, dataset, token,dataset_link):
|
| 23 |
"""
|
| 24 |
Update the transcriptions in the dataset and push it back to the Hugging Face Hub.
|
|
@@ -75,15 +85,6 @@ def main():
|
|
| 75 |
original_df.loc[original_df["index"] == row["index"], "transcription"] = row["transcription"]
|
| 76 |
|
| 77 |
return "update Successful"
|
| 78 |
-
|
| 79 |
-
def delete_empty_rows(updated_df):
|
| 80 |
-
"""
|
| 81 |
-
Delete rows marked for removal from the dataset.
|
| 82 |
-
"""
|
| 83 |
-
# Remove rows where transcription is empty or manually marked
|
| 84 |
-
updated_df = updated_df.dropna(subset=["transcription"])
|
| 85 |
-
updated_df = updated_df[updated_df["transcription"].str.strip() != ""]
|
| 86 |
-
return updated_df
|
| 87 |
|
| 88 |
def submit_changes(df, token,dataset_link):
|
| 89 |
"""
|
|
|
|
| 19 |
# print(df)
|
| 20 |
return df[["index", "transcription"]], dataset
|
| 21 |
|
| 22 |
+
|
| 23 |
+
def delete_empty_rows(updated_df):
|
| 24 |
+
"""
|
| 25 |
+
Delete rows marked for removal from the dataset.
|
| 26 |
+
"""
|
| 27 |
+
# Remove rows where transcription is empty or manually marked
|
| 28 |
+
updated_df = updated_df.dropna(subset=["transcription"])
|
| 29 |
+
updated_df = updated_df[updated_df["transcription"].str.strip() != ""]
|
| 30 |
+
return updated_df
|
| 31 |
+
|
| 32 |
def update_transcriptions(df, dataset, token,dataset_link):
|
| 33 |
"""
|
| 34 |
Update the transcriptions in the dataset and push it back to the Hugging Face Hub.
|
|
|
|
| 85 |
original_df.loc[original_df["index"] == row["index"], "transcription"] = row["transcription"]
|
| 86 |
|
| 87 |
return "update Successful"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
|
| 89 |
def submit_changes(df, token,dataset_link):
|
| 90 |
"""
|