chrissewell/whisperX
1
0
Fork 0
mirror of https://github.com/m-bain/whisperX.git synced 2025-07-01 18:17:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #246 from m-bain/v3

Browse Source 
V3
This commit is contained in:
Max Bain
2023-05-13 12:18:09 +01:00
committed by GitHub
parent 46b416296f 9ffb7e7a23
commit d8a2b4ffc9
7 changed files with 18 additions and 119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
whisperx/asr.py
View File

@ -14,7 +14,7 @@ from .vad import load_vad_model, merge_chunks
from .types import TranscriptionResult, SingleSegment
def load_model(whisper_arch, device, compute_type="float16", asr_options=None, language=None,
vad_options=None, model=None):
vad_options=None, model=None, task="transcribe"):
'''Load a Whisper model for inference.
Args:
whisper_arch: str - The name of the Whisper model to load.
@ -31,7 +31,7 @@ def load_model(whisper_arch, device, compute_type="float16", asr_options=None, l
model = WhisperModel(whisper_arch, device=device, compute_type=compute_type)
if language is not None:
tokenizer = faster_whisper.tokenizer.Tokenizer(model.hf_tokenizer, model.model.is_multilingual, task="transcribe", language=language)
tokenizer = faster_whisper.tokenizer.Tokenizer(model.hf_tokenizer, model.model.is_multilingual, task=task, language=language)
else:
print("No language specified, language will be first be detected for each audio file (increases inference time).")
tokenizer = None