Skip to content

Add --language option to select transcription language #95

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

Open
dmac100 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add --language option to select transcription language #95

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 3 additions & 2 deletions whisper_mic/cli.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,11 +22,12 @@
@click.option("--list_devices",default=False, help="Flag to list devices", is_flag=True,type=bool)
@click.option("--faster",default=False, help="Use faster_whisper implementation", is_flag=True,type=bool)
@click.option("--hallucinate_threshold",default=400, help="Raise this to reduce hallucinations. Lower this to activate more often.", is_flag=False,type=int)
def main(model: str, english: bool, verbose: bool, energy: int, pause: float, dynamic_energy: bool, save_file: bool, device: str, loop: bool, dictate: bool,mic_index:Optional[int],list_devices: bool,faster: bool,hallucinate_threshold:int) -> None:
@click.option("--language",default=None, help="The language to use", type=str)
def main(model: str, english: bool, verbose: bool, energy: int, pause: float, dynamic_energy: bool, save_file: bool, device: str, loop: bool, dictate: bool,mic_index:Optional[int],list_devices: bool,faster: bool,hallucinate_threshold:int,language: str) -> None:
if list_devices:
print("Possible devices: ",sr.Microphone.list_microphone_names())
return
mic = WhisperMic(model=model, english=english, verbose=verbose, energy=energy, pause=pause, dynamic_energy=dynamic_energy, save_file=save_file, device=device,mic_index=mic_index,implementation=("faster_whisper" if faster else "whisper"),hallucinate_threshold=hallucinate_threshold)
mic = WhisperMic(model=model, english=english, verbose=verbose, energy=energy, pause=pause, dynamic_energy=dynamic_energy, save_file=save_file, device=device,mic_index=mic_index,implementation=("faster_whisper" if faster else "whisper"),hallucinate_threshold=hallucinate_threshold,language=language)

if not loop:
try:
Expand Down
5 changes: 3 additions & 2 deletions whisper_mic/whisper_mic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@
# asound = cdll.LoadLibrary('libasound.so')
# asound.snd_lib_error_set_handler(c_error_handler)
class WhisperMic:
def __init__(self,model="base",device=("cuda" if torch.cuda.is_available() else "cpu"),english=False,verbose=False,energy=300,pause=2,dynamic_energy=False,save_file=False, model_root="~/.cache/whisper",mic_index=None,implementation="whisper",hallucinate_threshold=300):
def __init__(self,model="base",device=("cuda" if torch.cuda.is_available() else "cpu"),english=False,verbose=False,energy=300,pause=2,dynamic_energy=False,save_file=False, model_root="~/.cache/whisper",mic_index=None,implementation="whisper",hallucinate_threshold=300,language=None):

self.logger = get_logger("whisper_mic", "info")
self.energy = energy
Expand All @@ -35,6 +35,7 @@ def __init__(self,model="base",device=("cuda" if torch.cuda.is_available() else
self.verbose = verbose
self.english = english
self.keyboard = pynput.keyboard.Controller()
self.language = 'english' if english else language

self.platform = platform.system().lower()
if self.platform == "darwin":
Expand Down Expand Up @@ -179,7 +180,7 @@ def __transcribe(self,data=None, realtime: bool = False) -> None:
if self.english:
result = self.audio_model.transcribe(audio_data,language='english',suppress_tokens="")
else:
result = self.audio_model.transcribe(audio_data,suppress_tokens="")
result = self.audio_model.transcribe(audio_data,language=self.language,suppress_tokens="")
predicted_text = result["text"]

if not self.verbose:
Expand Down