Merge pull request #190 from agwosdz/bug-cache_align_model

"/" in whisper align model string get interpreted as path
rakuri255 · Dec 17, 2024 · e9eba04 · e9eba04
2 parents d2aa24e + e74c961
commit e9eba04
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/requirements.txt b/requirements.txt
@@ -70,7 +70,7 @@ contourpy==1.2.1
     # via matplotlib
 crepe==0.0.15
     # via -r requirements.in
-ctranslate2==4.3.1
+ctranslate2==4.4.0
     # via faster-whisper
 cycler==0.12.1
     # via matplotlib

diff --git a/src/UltraSinger.py b/src/UltraSinger.py
@@ -468,8 +468,10 @@ def CreateProcessAudio(process_data) -> str:
 def transcribe_audio(cache_folder_path: str, processing_audio_path: str) -> TranscriptionResult:
     """Transcribe audio with AI"""
     transcription_result = None
+    whisper_align_model_string = None
     if settings.transcriber == "whisper":
-        transcription_config = f"{settings.transcriber}_{settings.whisper_model.value}_{settings.pytorch_device}_{settings.whisper_align_model}_{settings.whisper_align_model}_{settings.whisper_batch_size}_{settings.whisper_compute_type}_{settings.language}"
+        if not settings.whisper_align_model is None: whisper_align_model_string = settings.whisper_align_model.replace("/", "_")
+        transcription_config = f"{settings.transcriber}_{settings.whisper_model.value}_{settings.pytorch_device}_{whisper_align_model_string}_{settings.whisper_batch_size}_{settings.whisper_compute_type}_{settings.language}"
         transcription_path = os.path.join(cache_folder_path, f"{transcription_config}.json")
         cached_transcription_available = check_file_exists(transcription_path)
         if settings.skip_cache_transcription or not cached_transcription_available: