remove loop
Browse files- asr.py +16 -15
- audio_plus_hash_uniq_07102024.csv +0 -0
- csv_processor.py +4 -3
asr.py
CHANGED
|
@@ -46,21 +46,22 @@ def safe_process_file(file_obj):
|
|
| 46 |
|
| 47 |
def transcribe_multiple_files(audio_files, lang, transcription):
|
| 48 |
transcriptions = []
|
| 49 |
-
for audio_file in audio_files:
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
|
|
|
| 64 |
|
| 65 |
@spaces.GPU
|
| 66 |
def transcribe_file(model, audio_samples, lang, user_transcription):
|
|
|
|
| 46 |
|
| 47 |
def transcribe_multiple_files(audio_files, lang, transcription):
|
| 48 |
transcriptions = []
|
| 49 |
+
# for audio_file in audio_files:
|
| 50 |
+
try:
|
| 51 |
+
audio_samples, sr, safe_name = safe_process_file(audio_files)
|
| 52 |
+
logger.debug(f"Transcribing file: {safe_name}")
|
| 53 |
+
logger.debug(f"Language selected: {lang}")
|
| 54 |
+
logger.debug(f"User-provided transcription: {transcription}")
|
| 55 |
+
|
| 56 |
+
result = transcribe_file(model, audio_samples, lang, transcription)
|
| 57 |
+
logger.debug(f"Transcription result: {result}")
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
transcriptions.append(f"File: {safe_name}\nTranscription: {result}\n")
|
| 61 |
+
except Exception as e:
|
| 62 |
+
logger.error(f"Error in transcription process: {str(e)}")
|
| 63 |
+
transcriptions.append(f"Error processing file: {str(e)}\n")
|
| 64 |
+
# return "\n".join(transcriptions)
|
| 65 |
|
| 66 |
@spaces.GPU
|
| 67 |
def transcribe_file(model, audio_samples, lang, user_transcription):
|
audio_plus_hash_uniq_07102024.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
csv_processor.py
CHANGED
|
@@ -14,7 +14,7 @@ def hash_md5(filepath):
|
|
| 14 |
|
| 15 |
import csv
|
| 16 |
|
| 17 |
-
def update_csv(file_path, search_hash, new_path, new_transcription):
|
| 18 |
# Use read/write mode to modify the relevant line or append if not found
|
| 19 |
with open(file_path, mode='r+', newline='', encoding='utf-8') as file:
|
| 20 |
reader = csv.DictReader(file)
|
|
@@ -24,8 +24,8 @@ def update_csv(file_path, search_hash, new_path, new_transcription):
|
|
| 24 |
|
| 25 |
# Locate the row with the matching hash
|
| 26 |
for i, row in enumerate(rows):
|
| 27 |
-
if row['hash'] == search_hash:
|
| 28 |
-
rows[i]['
|
| 29 |
rows[i]['transcription'] = new_transcription
|
| 30 |
found = True
|
| 31 |
break
|
|
@@ -42,6 +42,7 @@ def update_csv(file_path, search_hash, new_path, new_transcription):
|
|
| 42 |
writer = csv.DictWriter(append_file, fieldnames=fieldnames)
|
| 43 |
writer.writerow({
|
| 44 |
'hash': search_hash,
|
|
|
|
| 45 |
'filepath': new_path,
|
| 46 |
'transcription': new_transcription
|
| 47 |
})
|
|
|
|
| 14 |
|
| 15 |
import csv
|
| 16 |
|
| 17 |
+
def update_csv(file_path, search_hash, hash_16000, new_path, new_transcription):
|
| 18 |
# Use read/write mode to modify the relevant line or append if not found
|
| 19 |
with open(file_path, mode='r+', newline='', encoding='utf-8') as file:
|
| 20 |
reader = csv.DictReader(file)
|
|
|
|
| 24 |
|
| 25 |
# Locate the row with the matching hash
|
| 26 |
for i, row in enumerate(rows):
|
| 27 |
+
if row['hash'] == search_hash or row['hash_16000'] == search_hash:
|
| 28 |
+
rows[i]['hash_16000'] = hash_16000
|
| 29 |
rows[i]['transcription'] = new_transcription
|
| 30 |
found = True
|
| 31 |
break
|
|
|
|
| 42 |
writer = csv.DictWriter(append_file, fieldnames=fieldnames)
|
| 43 |
writer.writerow({
|
| 44 |
'hash': search_hash,
|
| 45 |
+
'hash_16000': hash_16000,
|
| 46 |
'filepath': new_path,
|
| 47 |
'transcription': new_transcription
|
| 48 |
})
|