fix building

app.py

@@ -51,11 +51,11 @@ logger = logging.getLogger(__name__)
 
 # Prepare language options for Dropdown
 language_options = [f"{k} ({v})" for k, v in ASR_LANGUAGES.items()]
-bam_index = 0
-try:
-    bam_index = language_options.index("bam")
-except ValueError:
-    bam_index = 0
+# bam_index = 0
+# try:
+#     bam_index = language_options.index("bam")
+# except ValueError:
+#     bam_index = 0
 
 
 mms_transcribe = gr.Interface(
@@ -65,7 +65,7 @@ mms_transcribe = gr.Interface(
         gr.Dropdown(
             choices=language_options,
             label="Language",
-            value=language_options[bam_index] if language_options else None,
+            value=language_options[0] if language_options else None,
         ),
         gr.Textbox(label="Optional: Provide your own transcription"),
     ],

csv_processor.py

@@ -0,0 +1,47 @@
+import hashlib
+import csv
+
+
+def hash_md5(filepath):
+    md5_hash = hashlib.md5()
+    try:
+        with open(filepath, "rb") as file:
+            for chunk in iter(lambda: file.read(128 * md5_hash.block_size), b''):
+                md5_hash.update(chunk)
+        return md5_hash.hexdigest()
+    except Exception as e:
+        return str(e)
+
+import csv
+
+def update_csv(file_path, search_hash, new_path, new_transcription):
+    # Use read/write mode to modify the relevant line or append if not found
+    with open(file_path, mode='r+', newline='', encoding='utf-8') as file:
+        reader = csv.DictReader(file)
+        fieldnames = reader.fieldnames
+        rows = list(reader)
+        found = False
+        
+        # Locate the row with the matching hash
+        for i, row in enumerate(rows):
+            if row['hash'] == search_hash:
+                rows[i]['filepath'] = new_path
+                rows[i]['transcription'] = new_transcription
+                found = True
+                break
+        
+        if found:
+            # Move file pointer to the beginning and write only the updated row
+            file.seek(0)  # Go to the beginning of the file
+            writer = csv.DictWriter(file, fieldnames=fieldnames)
+            writer.writeheader()  # Ensure the header is written
+            writer.writerows(rows)  # Write all rows back, with the updated one
+        return 
+    # Append a new row if the hash is not found
+    with open(file_path, mode='a', newline='', encoding='utf-8') as append_file:
+        writer = csv.DictWriter(append_file, fieldnames=fieldnames)
+        writer.writerow({
+            'hash': search_hash,
+            'filepath': new_path,
+            'transcription': new_transcription
+        })