"""Choosing hardware""" device = 'cuda' if torch.cuda.is_available() else 'cpu' if device == "cuda": print( "Using GPU. Setting default tensor type to torch.cuda.FloatTensor") torch.set_default_tensor_type("torch.cuda.FloatTensor") else: print("Using CPU. Setting default tensor type to torch.FloatTensor") torch.set_default_tensor_type("torch.FloatTensor") """Converting model to specified hardware and format""" acoustic_cfg_json = json.load( open(args.acoustic_model.replace(".torch", ".json"), "r")) acoustic_cfg = AcousticConfig.from_json(acoustic_cfg_json) acoustic_model = CNN(acoustic_cfg) acoustic_model.float().to(device) try: acoustic_model.load_state_dict(torch.load(args.acoustic_model)) except: print( "Failed to load model from {} without device mapping. Trying to load with mapping to {}" .format(args.acoustic_model, device)) acoustic_model.load_state_dict( torch.load(args.acoustic_model, map_location=device)) linguistic_cfg_json = json.load( open(args.linguistic_model.replace(".torch", ".json"), "r")) linguistic_cfg = LinguisticConfig.from_json(linguistic_cfg_json) linguistic_model = AttentionModel(linguistic_cfg) linguistic_model.float().to(device)
write(TMP_FILENAME, SAMPLE_RATE, myrecording) # Save as WAV file from deepspeech_generator import speech_to_text transcription = speech_to_text(join(args.deepspeech, "output_graph.pbmm"), join(args.deepspeech, "alphabet.txt"), join(args.deepspeech, "lm.binary"), join(args.deepspeech, "trie"), TMP_FILENAME) print(transcription) """Converting model to specified hardware and format""" acoustic_cfg_json = json.load( open(args.acoustic_model.replace(".torch", ".json"), "r")) acoustic_cfg = AcousticSpectrogramConfig.from_json(acoustic_cfg_json) acoustic_model = CNN(acoustic_cfg) acoustic_model.float().to("cpu") try: acoustic_model.load_state_dict(torch.load(args.acoustic_model)) except: print( "Failed to load model from {} without device mapping. Trying to load with mapping to {}" .format(args.acoustic_model, "cpu")) acoustic_model.load_state_dict( torch.load(args.acoustic_model, map_location="cpu")) acoustic_model.eval() linguistic_cfg_json = json.load( open(args.linguistic_model.replace(".torch", ".json"), "r")) linguistic_cfg = LinguisticConfig.from_json(linguistic_cfg_json)