kdllib.py 文件源码

def fetch_fruitspeech_softmax():
    fs, d, wav_names = fetch_sample_speech_fruit()
    def matcher(name):
        return name.split("/")[1]

    classes = [matcher(wav_name) for wav_name in wav_names]
    all_chars = [c for c in sorted(list(set("".join(classes))))]
    char2code = {v: k for k, v in enumerate(all_chars)}
    vocabulary_size = len(char2code.keys())
    y = []
    for n, cl in enumerate(classes):
        y.append(tokenize_ind(cl, char2code))

    # Is it kosher to kmeans on all the data?
    X, _apply, _re = apply_lpc_softmax_preproc(d)

    """
    for n, Xi in enumerate(X[::8]):
        di = _re(Xi)
        wavfile.write("t_%i.wav" % n, fs, soundsc(di))

    raise ValueError()
    """

    speech = {}
    speech["vocabulary_size"] = vocabulary_size
    speech["vocabulary"] = char2code
    speech["sample_rate"] = fs
    speech["data"] = X
    speech["target"] = y
    speech["reconstruct"] = _re
    return speech