From 9afc2c76737546e37e882f2446583f04f7f4912e Mon Sep 17 00:00:00 2001
From: Peter Staar <taa@zurich.ibm.com>
Date: Mon, 23 Jun 2025 15:44:14 +0200
Subject: [PATCH] added minimal_asr_pipeline

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
---
 docs/examples/minimal_asr_pipeline.py | 49 +++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)
 create mode 100644 docs/examples/minimal_asr_pipeline.py

diff --git a/docs/examples/minimal_asr_pipeline.py b/docs/examples/minimal_asr_pipeline.py
new file mode 100644
index 00000000..8a487d94
--- /dev/null
+++ b/docs/examples/minimal_asr_pipeline.py
@@ -0,0 +1,49 @@
+from pathlib import Path
+
+from docling.datamodel import asr_model_specs
+from docling.datamodel.base_models import ConversionStatus, InputFormat
+from docling.datamodel.document import ConversionResult
+from docling.datamodel.pipeline_options import AsrPipelineOptions
+from docling.document_converter import AudioFormatOption, DocumentConverter
+from docling.pipeline.asr_pipeline import AsrPipeline
+
+
+def get_asr_converter():
+    """Create a DocumentConverter configured for ASR with whisper_turbo model."""
+    pipeline_options = AsrPipelineOptions()
+    pipeline_options.asr_options = asr_model_specs.WHISPER_TURBO
+
+    converter = DocumentConverter(
+        format_options={
+            InputFormat.AUDIO: AudioFormatOption(
+                pipeline_cls=AsrPipeline,
+                pipeline_options=pipeline_options,
+            )
+        }
+    )
+    return converter
+
+
+def asr_pipeline_conversion(audio_path:Path) -> DoclingDocument:
+    """ASR pipeline conversion using whisper_turbo"""
+    # Check if the test audio file exists
+    assert audio_path.exists(), f"Test audio file not found: {audio_path}"
+
+    converter = get_asr_converter()
+
+    # Convert the audio file
+    result: ConversionResult = converter.convert(audio_path)
+
+    # Verify conversion was successful
+    assert result.status == ConversionStatus.SUCCESS, (
+        f"Conversion failed with status: {result.status}"
+    )
+    return result.document
+
+
+if __name__=="__main__":
+
+    audio_path = Path("<audio-file.wav/mp3>")
+
+    doc = asr_pipeline_conversion(audio_path=audio_path)
+    print(doc.export_to_markdown())