Add support for generator_default on redacting audio (#59)

* adding generator_default to audio file redaction

* removing reference to mp4

* update version

Author: akamor

docs/source/redact/redacting_audio.rst

@@ -35,4 +35,4 @@ Note that calling this method requires that pydub be installed in addition to th
 
 Additional Remarks
 ------------------
-When using the Textual Cloud (https://textual.tonic.ai) file uploads are limited to 25MB or less.  Supported file types are m4a, mp3, webm, mp4, mpga, wav.
+When using the Textual Cloud (https://textual.tonic.ai) file uploads are limited to 25MB or less.  Supported file types are m4a, mp3, webm, mpga, wav.

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "tonic-textual"
-version = "3.10.3"
+version = "3.10.4"
 description = "Wrappers around the Tonic Textual API"
 authors = ["Adam Kamor <[email protected]>", "Joe Ferrara <[email protected]>", "Ander Steele <[email protected]>", "Ethan Philpott <[email protected]>", "Lyon Van Voorhis <[email protected]>", "Kirill Medvedev <[email protected]>", "Travis Matthews <[email protected]>"]
 license = "MIT"

tonic_textual/__init__.py

@@ -1 +1 @@
-__version__ = "3.10.2"
+__version__ = "3.10.4"

tonic_textual/redact_api.py

@@ -247,7 +247,7 @@ def redact_audio(
         num_retries: Optional[int] = 30,
         wait_between_retries: Optional[int] = 10,
     ) -> RedactionResponse:
-        """Redacts the transcription from the provided audio file.  Supports m4a, mp3, webm, mp4, mpga, wav.  Limited to 25MB or less per API call.
+        """Redacts the transcription from the provided audio file.  Supports m4a, mp3, webm, mpga, wav.  Limited to 25MB or less per API call.
         Parameters
         ----------
         file_path : str
@@ -384,7 +384,7 @@ def get_audio_transcription(
         num_retries: Optional[int] = 30,
         wait_between_retries: Optional[int] = 10,
     ) -> TranscriptionResult:
-        """Redacts the transcription from the provided audio file.  Supports m4a, mp3, webm, mp4, mpga, wav.  Limited to 25MB or less per API call.
+        """Redacts the transcription from the provided audio file.  Supports m4a, mp3, webm, mpga, wav.  Limited to 25MB or less per API call.
         Parameters
         ----------
         file_path : str
@@ -458,6 +458,7 @@ def redact_audio_file(
         self,
         audio_file_path: str,
         output_file_path: str,
+        generator_default: PiiState = PiiState.Redaction,
         generator_config: Dict[str, PiiState] = dict(),
         label_block_lists: Optional[Dict[str, List[str]]] = None,
         label_allow_lists: Optional[Dict[str, List[str]]] = None,
@@ -471,17 +472,22 @@ def redact_audio_file(
         ----------
         audio_file_path : str
             The path to the input audio file.
-            Supported file types are wav, mp3, ogg, flv, mp4, wma, aac, and others. See
+            Supported file types are wav, mp3, ogg, flv, wma, aac, and others. See
             https://github.com/jiaaro/pydub for complete information on file types
             supported.
 
         output_file_path : str
             The path to save the redacted output file. The output file path specifies
             the audio file type that the output is written as via it's extension.
-            Supported file types are wav, mp3, ogg, flv, mp4, wma, and aac. See
+            Supported file types are wav, mp3, ogg, flv, wma, and aac. See
             https://github.com/jiaaro/pydub for complete information on file types
             supported.
-
+        
+        generator_default: PiiState = PiiState.Redaction
+            The default redaction used for types that are not specified in
+            generator_config. Value must be one of "Redaction", "Synthesis", or
+            "Off".
+            
         generator_config: Dict[str, PiiState]
             A dictionary of sensitive data entities. For each entity, indicates
             whether to redact, synthesize, or ignore it. Values must be one of
@@ -530,7 +536,7 @@ def redact_audio_file(
         transcription = self.get_audio_transcription(audio_file_path)
         de_id_res = self.redact(
             transcription.text,
-            generator_default=PiiState.Redaction,
+            generator_default=generator_default,
             generator_config=generator_config,
             generator_metadata=dict(),
             random_seed=None,