mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-27 04:24:45 +00:00
Updated README and added ASR example
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
This commit is contained in:
parent
9afc2c7673
commit
687241e8a6
7
docs/examples/minimal_asr_pipeline.py
vendored
7
docs/examples/minimal_asr_pipeline.py
vendored
@ -1,5 +1,7 @@
|
|||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
|
|
||||||
|
from docling_core.types.doc import DoclingDocument
|
||||||
|
|
||||||
from docling.datamodel import asr_model_specs
|
from docling.datamodel import asr_model_specs
|
||||||
from docling.datamodel.base_models import ConversionStatus, InputFormat
|
from docling.datamodel.base_models import ConversionStatus, InputFormat
|
||||||
from docling.datamodel.document import ConversionResult
|
from docling.datamodel.document import ConversionResult
|
||||||
@ -24,7 +26,7 @@ def get_asr_converter():
|
|||||||
return converter
|
return converter
|
||||||
|
|
||||||
|
|
||||||
def asr_pipeline_conversion(audio_path:Path) -> DoclingDocument:
|
def asr_pipeline_conversion(audio_path: Path) -> DoclingDocument:
|
||||||
"""ASR pipeline conversion using whisper_turbo"""
|
"""ASR pipeline conversion using whisper_turbo"""
|
||||||
# Check if the test audio file exists
|
# Check if the test audio file exists
|
||||||
assert audio_path.exists(), f"Test audio file not found: {audio_path}"
|
assert audio_path.exists(), f"Test audio file not found: {audio_path}"
|
||||||
@ -41,8 +43,7 @@ def asr_pipeline_conversion(audio_path:Path) -> DoclingDocument:
|
|||||||
return result.document
|
return result.document
|
||||||
|
|
||||||
|
|
||||||
if __name__=="__main__":
|
if __name__ == "__main__":
|
||||||
|
|
||||||
audio_path = Path("<audio-file.wav/mp3>")
|
audio_path = Path("<audio-file.wav/mp3>")
|
||||||
|
|
||||||
doc = asr_pipeline_conversion(audio_path=audio_path)
|
doc = asr_pipeline_conversion(audio_path=audio_path)
|
||||||
|
Loading…
Reference in New Issue
Block a user