lashman/whisper_voice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

v1.0.1 updates and polish

Browse Source
This commit is contained in:
lashman
2026-01-24 18:29:10 +02:00
parent de64610a90
commit 19831656dc
11 changed files with 342 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/core/transcriber.py
View File

@@ -74,11 +74,11 @@ class WhisperTranscriber:
logging.error(f"Failed to load model: {e}")
self.model = None
def transcribe(self, audio_data, is_file: bool = False) -> str:
def transcribe(self, audio_data, is_file: bool = False, task: Optional[str] = None) -> str:
"""
Transcribe audio data.
"""
logging.info(f"Starting transcription... (is_file={is_file})")
logging.info(f"Starting transcription... (is_file={is_file}, task={task})")
# Ensure model is loaded
if not self.model:
@@ -91,6 +91,10 @@ class WhisperTranscriber:
beam_size = int(self.config.get("beam_size"))
best_of = int(self.config.get("best_of"))
vad = False if is_file else self.config.get("vad_filter")
language = self.config.get("language")
# Use task override if provided, otherwise config
final_task = task if task else self.config.get("task")
# Transcribe
segments, info = self.model.transcribe(
@@ -98,6 +102,8 @@ class WhisperTranscriber:
beam_size=beam_size,
best_of=best_of,
vad_filter=vad,
task=final_task,
language=language if language != "auto" else None,
vad_parameters=dict(min_silence_duration_ms=500),
condition_on_previous_text=self.config.get("condition_on_previous_text"),
without_timestamps=True