Skip to content

Add audio redaction quality #66

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 9 commits into from
Apr 19, 2024
Merged

Add audio redaction quality #66

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
141c804
Add audio redaction quality
dweekly Apr 12, 2024
7d223cf
Update assemblyai/types.py
dweekly Apr 19, 2024
086025b
Update assemblyai/types.py
dweekly Apr 19, 2024
a54f8c4
Update assemblyai/types.py
dweekly Apr 19, 2024
f2c97c8
Update assemblyai/types.py
dweekly Apr 19, 2024
bdf036a
Update assemblyai/types.py
dweekly Apr 19, 2024
2aaf9dc
Rename to PIIRedactedAudioQuality
dweekly Apr 19, 2024
3a8db55
Add PIIRedactedAudioQuality to types.
dweekly Apr 19, 2024
4322b6c
import type in `__init__.py`
ploeber Apr 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions assemblyai/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@
LemurTaskResponse,
LemurTranscriptSource,
Paragraph,
PIIRedactedAudioQuality,
PIIRedactionPolicy,
PIISubstitutionPolicy,
RawTranscriptionConfig,
Expand Down Expand Up @@ -97,8 +98,6 @@
"LemurQuestionResponse",
"LemurSummaryResponse",
"LemurTaskResponse",
"PIIRedactionPolicy",
"PIISubstitutionPolicy",
"Sentence",
"Sentiment",
"SentimentType",
Expand All @@ -117,6 +116,7 @@
"Utterance",
"UtteranceWord",
"Paragraph",
"PIIRedactedAudioQuality",
"PIISubstitutionPolicy",
"PIIRedactionPolicy",
"RawTranscriptionConfig",
Expand Down
22 changes: 22 additions & 0 deletions assemblyai/types.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,6 +202,11 @@ class WordBoost(str, Enum):
high = "high"


class PIIRedactedAudioQuality(str, Enum):
mp3 = "mp3"
wav = "wav"


class EntityType(str, Enum):
"""
Used for AssemblyAI's Entity Detection feature.
Expand Down Expand Up @@ -454,6 +459,8 @@ class RawTranscriptionConfig(BaseModel):
"Redact PII from the transcribed text."
redact_pii_audio: Optional[bool]
"Generate a copy of the original media file with spoken PII 'beeped' out."
redact_pii_audio_quality: Optional[PIIRedactedAudioQuality]
"The quality of the redacted audio file in case `redact_pii_audio` is enabled."
redact_pii_policies: Optional[List[PIIRedactionPolicy]]
"The list of PII Redaction policies to enable."
redact_pii_sub: Optional[PIISubstitutionPolicy]
Expand Down Expand Up @@ -543,6 +550,7 @@ def __init__(
filter_profanity: Optional[bool] = None,
redact_pii: Optional[bool] = None,
redact_pii_audio: Optional[bool] = None,
redact_pii_audio_quality: Optional[PIIRedactedAudioQuality] = None,
redact_pii_policies: Optional[List[PIIRedactionPolicy]] = None,
redact_pii_sub: Optional[PIISubstitutionPolicy] = None,
speaker_labels: Optional[bool] = None,
Expand Down Expand Up @@ -580,6 +588,7 @@ def __init__(
filter_profanity: Filter profanity from the transcribed text.
redact_pii: Redact PII from the transcribed text.
redact_pii_audio: Generate a copy of the original media file with spoken PII 'beeped' out (new audio only available for 24 hours).
redact_pii_audio_quality: The quality of the redacted audio file in case `redact_pii_audio` is enabled.
redact_pii_policies: The list of PII Redaction policies to enable.
redact_pii_sub: The replacement logic for detected PII.
speaker_labels: Enable Speaker Diarization.
Expand Down Expand Up @@ -623,6 +632,7 @@ def __init__(
self.set_redact_pii(
redact_pii,
redact_pii_audio,
redact_pii_audio_quality,
redact_pii_policies,
redact_pii_sub,
)
Expand Down Expand Up @@ -773,6 +783,12 @@ def redact_pii_audio(self) -> Optional[bool]:

return self._raw_transcription_config.redact_pii_audio

@property
def redact_pii_audio_quality(self) -> Optional[PIIRedactedAudioQuality]:
"The quality of the redacted audio file in case `redact_pii_audio` is enabled."

return self._raw_transcription_config.redact_pii_audio_quality

@property
def redact_pii_policies(self) -> Optional[List[PIIRedactionPolicy]]:
"Returns a list of set of defined PII redaction policies."
Expand Down Expand Up @@ -1122,6 +1138,7 @@ def set_redact_pii(
self,
enable: Optional[bool] = True,
redact_audio: Optional[bool] = None,
redact_audio_quality: Optional[PIIRedactedAudioQuality] = None,
policies: Optional[List[PIIRedactionPolicy]] = None,
substitution: Optional[PIISubstitutionPolicy] = None,
) -> Self:
Expand All @@ -1131,13 +1148,15 @@ def set_redact_pii(
Args:
enable: whether to enable or disable the PII Redaction feature.
redact_audio: Generate a copy of the original media file with spoken PII 'beeped' out. NOTE: The copy is available for 24h
redact_audio_quality: The quality of the redacted audio file in case `redact_audio` is enabled.
policies: A list of PII redaction policies to enable.
substitution: The replacement logic for detected PII (`PIISubstutionPolicy.hash` by default).
"""

if not enable:
self._raw_transcription_config.redact_pii = None
self._raw_transcription_config.redact_pii_audio = None
self._raw_transcription_config.redact_pii_audio_quality = None
self._raw_transcription_config.redact_pii_policies = None
self._raw_transcription_config.redact_pii_sub = None

Expand All @@ -1148,6 +1167,7 @@ def set_redact_pii(

self._raw_transcription_config.redact_pii = True
self._raw_transcription_config.redact_pii_audio = redact_audio
self._raw_transcription_config.redact_pii_audio_quality = redact_audio_quality
self._raw_transcription_config.redact_pii_policies = policies
self._raw_transcription_config.redact_pii_sub = substitution

Expand Down Expand Up @@ -1527,6 +1547,8 @@ class BaseTranscript(BaseModel):
"Redact PII from the transcribed text."
redact_pii_audio: Optional[bool]
"Generate a copy of the original media file with spoken PII 'beeped' out."
redact_pii_audio_quality: Optional[PIIRedactedAudioQuality]
"The quality of the redacted audio file in case `redact_pii_audio` is enabled."
redact_pii_policies: Optional[List[PIIRedactionPolicy]]
"The list of PII Redaction policies to enable."
redact_pii_sub: Optional[PIISubstitutionPolicy]
Expand Down