need to fix ruff linter

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

docling/backend/wav_backend.py

@@ -8,8 +8,8 @@ from docling.backend.abstract_backend import AbstractDocumentBackend
 from docling.datamodel.base_models import InputFormat
 from docling.datamodel.document import InputDocument
 
-class WavDocumentBackend(AbstractDocumentBackend):
 
+class WavDocumentBackend(AbstractDocumentBackend):
     def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
         super().__init__(in_doc, path_or_stream)
 
@@ -29,4 +29,3 @@ class WavDocumentBackend(AbstractDocumentBackend):
     @classmethod
     def supported_formats(cls) -> set[InputFormat]:
         return {InputFormat.WAV}
-

docling/cli/main.py

@@ -579,7 +579,6 @@ def convert(  # noqa: C901
             )
 
         else:
-            
             _log.error(f"Did not find the correct pipeline: {pipeline}")
 
         if artifacts_path is not None:

docling/datamodel/base_models.py

@@ -51,6 +51,7 @@ class InputFormat(str, Enum):
     # Audio
     WAV = "wav"
 
+
 class OutputFormat(str, Enum):
     MARKDOWN = "md"
     JSON = "json"
@@ -105,7 +106,6 @@ FormatToMimeType: Dict[InputFormat, List[str]] = {
     ],
     InputFormat.XML_USPTO: ["application/xml", "text/plain"],
     InputFormat.JSON_DOCLING: ["application/json"],
-
     # Audio
     InputFormat.WAV: ["audio/wav", "audio/x-wav"],
 }
@@ -165,6 +165,7 @@ class LayoutPrediction(BaseModel):
 class VlmPrediction(BaseModel):
     text: str = ""
 
+
 class AsrPrediction(BaseModel):
     text: str = ""
 

docling/datamodel/pipeline_options.py

@@ -257,10 +257,12 @@ class BaseVlmOptions(BaseModel):
     kind: str
     prompt: str
 
+
 class BaseAsrOptions(BaseModel):
     kind: str
     prompt: str
 
+
 class ResponseFormat(str, Enum):
     DOCTAGS = "doctags"
     MARKDOWN = "markdown"
@@ -274,6 +276,7 @@ class InferenceFramework(str, Enum):
     # Audio
     ASR_NEMO = "asr_nemo"
 
+
 class HuggingFaceVlmOptions(BaseVlmOptions):
     kind: Literal["hf_model_options"] = "hf_model_options"
 
@@ -289,6 +292,7 @@ class HuggingFaceVlmOptions(BaseVlmOptions):
     def repo_cache_folder(self) -> str:
         return self.repo_id.replace("/", "--")
 
+
 class HuggingFaceAsrOptions(BaseVlmOptions):
     kind: Literal["hf_model_options"] = "hf_model_options"
 
@@ -304,6 +308,7 @@ class HuggingFaceAsrOptions(BaseVlmOptions):
     def repo_cache_folder(self) -> str:
         return self.repo_id.replace("/", "--")
 
+
 class ApiVlmOptions(BaseVlmOptions):
     kind: Literal["api_model_options"] = "api_model_options"
 
@@ -415,10 +420,10 @@ class VlmPipelineOptions(PaginatedPipelineOptions):
         smoldocling_vlm_conversion_options
     )
 
+
 class AsrPipelineOptions(PaginatedPipelineOptions):
-    asr_options: Union[HuggingFaceAsrOptions] = (
-        asr_nemo_conversion_options
-    )
+    asr_options: Union[HuggingFaceAsrOptions] = asr_nemo_conversion_options
+
 
 class PdfPipelineOptions(PaginatedPipelineOptions):
     """Options for the PDF pipeline."""

docling/document_converter.py

@@ -19,9 +19,9 @@ from docling.backend.md_backend import MarkdownDocumentBackend
 from docling.backend.msexcel_backend import MsExcelDocumentBackend
 from docling.backend.mspowerpoint_backend import MsPowerpointDocumentBackend
 from docling.backend.msword_backend import MsWordDocumentBackend
+from docling.backend.wav_backend import WavDocumentBackend
 from docling.backend.xml.jats_backend import JatsDocumentBackend
 from docling.backend.xml.uspto_backend import PatentUsptoDocumentBackend
-from docling.backend.wav_backend import WavDocumentBackend
 from docling.datamodel.base_models import (
     ConversionStatus,
     DoclingComponentType,
@@ -34,7 +34,7 @@ from docling.datamodel.document import (
     InputDocument,
     _DocumentConversionInput,
 )
-from docling.datamodel.pipeline_options import PipelineOptions, AsrPipelineOptions
+from docling.datamodel.pipeline_options import AsrPipelineOptions, PipelineOptions
 from docling.datamodel.settings import (
     DEFAULT_PAGE_RANGE,
     DocumentLimits,
@@ -42,10 +42,10 @@ from docling.datamodel.settings import (
     settings,
 )
 from docling.exceptions import ConversionError
+from docling.pipeline.asr_pipeline import AsrPipeline
 from docling.pipeline.base_pipeline import BasePipeline
 from docling.pipeline.simple_pipeline import SimplePipeline
 from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
-from docling.pipeline.asr_pipeline import AsrPipeline
 from docling.utils.utils import chunkify
 
 _log = logging.getLogger(__name__)
@@ -119,9 +119,11 @@ class PdfFormatOption(FormatOption):
     pipeline_cls: Type = StandardPdfPipeline
     backend: Type[AbstractDocumentBackend] = DoclingParseV4DocumentBackend
 
+
 class AsrFormatOption(FormatOption):
     pipeline_cls: Type = AsrPipeline
 
+
 def _get_default_option(format: InputFormat) -> FormatOption:
     format_to_default_options = {
         InputFormat.CSV: FormatOption(

docling/models/hf_asr_models/asr_nemo.py

@@ -10,13 +10,13 @@ from docling.datamodel.pipeline_options import (
     AcceleratorOptions,
     HuggingFaceAsrOptions,
 )
-
 from docling.models.base_model import BasePageModel
 from docling.utils.accelerator_utils import decide_device
 from docling.utils.profiling import TimeRecorder
 
 _log = logging.getLogger(__name__)
 
+
 class AsrNemoModel(BasePageModel):
     def __init__(
         self,
@@ -45,7 +45,6 @@ class AsrNemoModel(BasePageModel):
             elif (artifacts_path / repo_cache_folder).exists():
                 artifacts_path = artifacts_path / repo_cache_folder
 
-            self.model = nemo_asr.models.ASRModel.from_pretrained("nvidia/parakeet-tdt-0.6b-v2")
-
-            
-            
+            self.model = nemo_asr.models.ASRModel.from_pretrained(
+                "nvidia/parakeet-tdt-0.6b-v2"
+            )

docling/pipeline/asr_pipeline.py

@@ -9,18 +9,16 @@ from docling.backend.abstract_backend import (
 )
 from docling.datamodel.base_models import ConversionStatus
 from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import PipelineOptions
-from docling.pipeline.base_pipeline import BasePipeline
-from docling.utils.profiling import ProfilingScope, TimeRecorder
-
 from docling.datamodel.pipeline_options import (
+    AsrPipelineOptions,
     HuggingFaceAsrOptions,
     InferenceFramework,
+    PipelineOptions,
     ResponseFormat,
-    AsrPipelineOptions,
 )
-
 from docling.models.hf_asr_models.asr_nemo import AsrNemoModel
+from docling.pipeline.base_pipeline import BasePipeline
+from docling.utils.profiling import ProfilingScope, TimeRecorder
 
 _log = logging.getLogger(__name__)
 
@@ -59,7 +57,7 @@ class AsrPipeline(BasePipeline):
                 _log.error(f"{asr_options.inference_framework} is not supported")
 
         else:
-            _log.error(f"ASR is not supported")
+            _log.error("ASR is not supported")
 
     def _build_document(self, conv_res: ConversionResult) -> ConversionResult:
         pass