avoid starting with space in transcript

This commit is contained in:
pyp_l40
2024-04-20 12:09:11 -05:00
parent 98a8abd4dd
commit 13e52470c3

View File

@@ -113,9 +113,11 @@ def load_models(whisper_backend_name, whisper_model_name, alignment_model_name,
def get_transcribe_state(segments): def get_transcribe_state(segments):
words_info = [word_info for segment in segments for word_info in segment["words"]] words_info = [word_info for segment in segments for word_info in segment["words"]]
transcript = " ".join([segment["text"] for segment in segments])
transcript = transcript[1:] if transcript[0] == " " else transcript
return { return {
"segments": segments, "segments": segments,
"transcript": " ".join([segment["text"] for segment in segments]), "transcript": transcript,
"words_info": words_info, "words_info": words_info,
"transcript_with_start_time": " ".join([f"{word['start']} {word['word']}" for word in words_info]), "transcript_with_start_time": " ".join([f"{word['start']} {word['word']}" for word in words_info]),
"transcript_with_end_time": " ".join([f"{word['word']} {word['end']}" for word in words_info]), "transcript_with_end_time": " ".join([f"{word['word']} {word['end']}" for word in words_info]),