
* scaffolding in place Signed-off-by: Peter Staar <taa@zurich.ibm.com> * doing scaffolding for audio pipeline Signed-off-by: Peter Staar <taa@zurich.ibm.com> * WIP: got first transcription working Signed-off-by: Peter Staar <taa@zurich.ibm.com> * all working, time to start cleaning up Signed-off-by: Peter Staar <taa@zurich.ibm.com> * first working ASR pipeline Signed-off-by: Peter Staar <taa@zurich.ibm.com> * added openai-whisper as a first transcription model Signed-off-by: Peter Staar <taa@zurich.ibm.com> * updating with asr_options Signed-off-by: Peter Staar <taa@zurich.ibm.com> * finalised the first working ASR pipeline with Whisper Signed-off-by: Peter Staar <taa@zurich.ibm.com> * use whisper from the latest git commit Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * Update docling/datamodel/pipeline_options.py Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> Signed-off-by: Peter W. J. Staar <91719829+PeterStaar-IBM@users.noreply.github.com> * Update docling/datamodel/pipeline_options.py Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> Signed-off-by: Peter W. J. Staar <91719829+PeterStaar-IBM@users.noreply.github.com> * updated comment Signed-off-by: Peter Staar <taa@zurich.ibm.com> * AudioBackend -> DummyBackend Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * file rename Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Rename to NoOpBackend, add test for ASR pipeline Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Support every format in NoOpBackend Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Add missing audio file and test Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Install ffmpeg system dependency for ASR test Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Peter W. J. Staar <91719829+PeterStaar-IBM@users.noreply.github.com> Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
52 lines
1.6 KiB
Python
52 lines
1.6 KiB
Python
import logging
|
|
from io import BytesIO
|
|
from pathlib import Path
|
|
from typing import Set, Union
|
|
|
|
from docling.backend.abstract_backend import AbstractDocumentBackend
|
|
from docling.datamodel.base_models import InputFormat
|
|
from docling.datamodel.document import InputDocument
|
|
|
|
_log = logging.getLogger(__name__)
|
|
|
|
|
|
class NoOpBackend(AbstractDocumentBackend):
|
|
"""
|
|
A no-op backend that only validates input existence.
|
|
Used e.g. for audio files where actual processing is handled by the ASR pipeline.
|
|
"""
|
|
|
|
def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
|
|
super().__init__(in_doc, path_or_stream)
|
|
|
|
_log.debug(f"NoOpBackend initialized for: {path_or_stream}")
|
|
|
|
# Validate input
|
|
try:
|
|
if isinstance(self.path_or_stream, BytesIO):
|
|
# Check if stream has content
|
|
self.valid = len(self.path_or_stream.getvalue()) > 0
|
|
_log.debug(
|
|
f"BytesIO stream length: {len(self.path_or_stream.getvalue())}"
|
|
)
|
|
elif isinstance(self.path_or_stream, Path):
|
|
# Check if file exists
|
|
self.valid = self.path_or_stream.exists()
|
|
_log.debug(f"File exists: {self.valid}")
|
|
else:
|
|
self.valid = False
|
|
except Exception as e:
|
|
_log.error(f"NoOpBackend validation failed: {e}")
|
|
self.valid = False
|
|
|
|
def is_valid(self) -> bool:
|
|
return self.valid
|
|
|
|
@classmethod
|
|
def supports_pagination(cls) -> bool:
|
|
return False
|
|
|
|
@classmethod
|
|
def supported_formats(cls) -> Set[InputFormat]:
|
|
return set(InputFormat)
|