Merge pull request #120 from snoesberger/add-multilingual-support

Add support for faster-whisper multilingual option

src/whisper_ctranslate2/commandline.py

@@ -364,6 +364,13 @@ def read_command_line():
             help="When using Batched transcription the maximum number of parallel requests to model for decoding.",
         )
 
+        algorithm_args.add_argument(
+            "--multilingual",
+            type=CommandLine._str2bool,
+            default=False,
+            help="Perform language detection on every segment",
+        )
+
         vad_args = parser.add_argument_group("VAD filter arguments")
 
         vad_args.add_argument(

src/whisper_ctranslate2/transcribe.py

@@ -52,6 +52,7 @@ class TranscriptionOptions(NamedTuple):
     vad_min_speech_duration_ms: Optional[int]
     vad_max_speech_duration_s: Optional[int]
     vad_min_silence_duration_ms: Optional[int]
+    multilingual: bool
 
 
 class Transcribe:
@@ -179,6 +180,7 @@ def inference(
             vad_filter=vad,
             vad_parameters=vad_parameters,
             **batch_size,
+            multilingual=options.multilingual,
         )
 
         language_name = LANGUAGES[info.language].title()

src/whisper_ctranslate2/whisper_ctranslate2.py

@@ -74,6 +74,7 @@ def get_transcription_options(args):
         vad_min_speech_duration_ms=args.pop("vad_min_speech_duration_ms"),
         vad_max_speech_duration_s=args.pop("vad_max_speech_duration_s"),
         vad_min_silence_duration_ms=args.pop("vad_min_silence_duration_ms"),
+        multilingual=args.pop("multilingual"),
     )