6cf660e622
- Allow filtering on Tenant Types & searching for parts of Tenant names - Implement health checks - Start Prometheus monitoring (needs to be finalized) - Refine audio_processor and srt_processor to reduce duplicate code and support for larger files - Introduce repopack to reason in LLMs about the code
35 lines
1.2 KiB
Python
35 lines
1.2 KiB
Python
from common.extensions import minio_client
|
|
from .transcription_processor import TranscriptionProcessor
|
|
import re
|
|
|
|
|
|
class SRTProcessor(TranscriptionProcessor):
|
|
def _get_transcription(self):
|
|
file_data = minio_client.download_document_file(
|
|
self.tenant.id,
|
|
self.document_version.doc_id,
|
|
self.document_version.language,
|
|
self.document_version.id,
|
|
self.document_version.file_name
|
|
)
|
|
srt_content = file_data.decode('utf-8')
|
|
return self._clean_srt(srt_content)
|
|
|
|
def _clean_srt(self, srt_content):
|
|
# Remove timecodes and subtitle numbers
|
|
cleaned_lines = []
|
|
for line in srt_content.split('\n'):
|
|
# Skip empty lines, subtitle numbers, and timecodes
|
|
if line.strip() and not line.strip().isdigit() and not re.match(
|
|
r'\d{2}:\d{2}:\d{2},\d{3} --> \d{2}:\d{2}:\d{2},\d{3}', line):
|
|
cleaned_lines.append(line.strip())
|
|
|
|
# Join the cleaned lines
|
|
cleaned_text = ' '.join(cleaned_lines)
|
|
|
|
# Remove any extra spaces
|
|
cleaned_text = re.sub(r'\s+', ' ', cleaned_text).strip()
|
|
|
|
return cleaned_text
|
|
|