Function model_inference

webui.py:141–179

(input_wav, language, fs=16000)

	return new_s.strip()

def model_inference(input_wav, language, fs=16000):
	# task_abbr = {"Speech Recognition": "ASR", "Rich Text Transcription": ("ASR", "AED", "SER")}
	language_abbr = {"auto": "auto", "zh": "zh", "en": "en", "yue": "yue", "ja": "ja", "ko": "ko",
					 "nospeech": "nospeech"}
	
	# task = "Speech Recognition" if task is None else task
	language = "auto" if len(language) < 1 else language
	selected_language = language_abbr[language]
	# selected_task = task_abbr.get(task)
	
	# print(f"input_wav: {type(input_wav)}, {input_wav[1].shape}, {input_wav}")
	
	if isinstance(input_wav, tuple):
		fs, input_wav = input_wav
		input_wav = input_wav.astype(np.float32) / np.iinfo(np.int16).max
		if len(input_wav.shape) > 1:
			input_wav = input_wav.mean(-1)
		if fs != 16000:
			print(f"audio_fs: {fs}")
			resampler = torchaudio.transforms.Resample(fs, 16000)
			input_wav_t = torch.from_numpy(input_wav).to(torch.float32)
			input_wav = resampler(input_wav_t[None, :])[0, :].numpy()
	
	
	merge_vad = True #False if selected_task == "ASR" else True
	print(f"language: {language}, merge_vad: {merge_vad}")
	text = model.generate(input=input_wav,
						  cache={},
						  language=language,
						  use_itn=True,
						  batch_size_s=60, merge_vad=merge_vad)
	
	print(text)
	text = text[0]["text"]
	text = format_str_v3(text)
	
	print(text)
	
	return text


audio_examples = [