mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: Describe examples (#2262)

Browse Source 
* Update .py examples with clearer guidance,
update out of date imports and calls

Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com>

* Fix minimal.py string error, fix ruff format error

Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com>

* fix more CI issues

Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com>

---------

Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com>
This commit is contained in:
Mingxuan Zhao
2025-09-16 10:00:38 -04:00
committed by GitHub
parent 0e95171dd6
commit ff351fd40c
21 changed files with 608 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
docs/examples/minimal_asr_pipeline.py vendored
View File

@@ -1,3 +1,28 @@
# %% [markdown]
# Minimal ASR pipeline example: transcribe an audio file to Markdown text.
#
# What this example does
# - Configures the ASR pipeline with a default model spec and converts one audio file.
# - Prints the recognized speech segments in Markdown with timestamps.
#
# Prerequisites
# - Install Docling with ASR extras and any audio dependencies (ffmpeg, etc.).
# - Ensure your environment can download or access the configured ASR model.
# - Some formats require ffmpeg codecs; install ffmpeg and ensure it's on PATH.
#
# How to run
# - From the repository root, run: `python docs/examples/minimal_asr_pipeline.py`.
# - The script prints the transcription to stdout.
#
# Customizing the model
# - Edit `get_asr_converter()` to switch `asr_model_specs` (e.g., language or model size).
# - Keep `InputFormat.AUDIO` and `AsrPipeline` unchanged for a minimal setup.
#
# Input audio
# - Defaults to `tests/data/audio/sample_10s.mp3`. Update `audio_path` to your own file if needed.
# %%
from pathlib import Path
from docling_core.types.doc import DoclingDocument
@@ -11,7 +36,11 @@ from docling.pipeline.asr_pipeline import AsrPipeline
def get_asr_converter():
"""Create a DocumentConverter configured for ASR with whisper_turbo model."""
"""Create a DocumentConverter configured for ASR with a default model.
Uses `asr_model_specs.WHISPER_TURBO` by default. You can swap in another
model spec from `docling.datamodel.asr_model_specs` to experiment.
"""
pipeline_options = AsrPipelineOptions()
pipeline_options.asr_options = asr_model_specs.WHISPER_TURBO
@@ -27,7 +56,7 @@ def get_asr_converter():
def asr_pipeline_conversion(audio_path: Path) -> DoclingDocument:
"""ASR pipeline conversion using whisper_turbo"""
"""Run the ASR pipeline and return a `DoclingDocument` transcript."""
# Check if the test audio file exists
assert audio_path.exists(), f"Test audio file not found: {audio_path}"