Python utils.load_spectrograms() Examples

The following are 3 code examples of utils.load_spectrograms(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module utils , or try the search function .
Example #1
Source File: eval.py    From tacotron with Apache License 2.0 5 votes vote down vote up 
def eval(): 
    # Load graph
    g = Graph(mode="eval"); print("Evaluation Graph loaded")

    # Load data
    fpaths, text_lengths, texts = load_data(mode="eval")

    # Parse
    text = np.fromstring(texts[0], np.int32) # (None,)
    fname, mel, mag = load_spectrograms(fpaths[0])

    x = np.expand_dims(text, 0) # (1, None)
    y = np.expand_dims(mel, 0) # (1, None, n_mels*r)
    z = np.expand_dims(mag, 0) # (1, None, n_mfccs)

    saver = tf.train.Saver()
    with tf.Session() as sess:
        saver.restore(sess, tf.train.latest_checkpoint(hp.logdir)); print("Restored!")

        writer = tf.summary.FileWriter(hp.logdir, sess.graph)

        # Feed Forward
        ## mel
        y_hat = np.zeros((1, y.shape[1], y.shape[2]), np.float32)  # hp.n_mels*hp.r
        for j in range(y.shape[1]):
            _y_hat = sess.run(g.y_hat, {g.x: x, g.y: y_hat})
            y_hat[:, j, :] = _y_hat[:, j, :]

        ## mag
        merged, gs = sess.run([g.merged, g.global_step], {g.x:x, g.y:y, g.y_hat: y_hat, g.z: z})
        writer.add_summary(merged, global_step=gs)
        writer.close()
Example #2
Source File: prepare_acoustic_features.py    From ophelia with Apache License 2.0 5 votes vote down vote up 
def proc(fpath, hp):
    
    if not os.path.isfile(fpath):
        return
        
    fname, mel, mag, full_mel = load_spectrograms(hp, fpath)
    np.save("{}/{}".format(hp.coarse_audio_dir, fname.replace("wav", "npy")), mel)
    np.save("{}/{}".format(hp.full_audio_dir, fname.replace("wav", "npy")), mag)
    np.save("{}/{}".format(hp.full_mel_dir, fname.replace("wav", "npy")), full_mel)
Example #3
Source File: evaluate.py    From tacotron with Apache License 2.0 4 votes vote down vote up 
def evaluate():
    # Load graph
    g = Graph(mode="evaluate"); print("Graph loaded")

    # Load data
    fpaths, _, texts = load_data(mode="evaluate")
    lengths = [len(t) for t in texts]
    maxlen = sorted(lengths, reverse=True)[0]
    new_texts = np.zeros((len(texts), maxlen), np.int32)
    for i, text in enumerate(texts):
        new_texts[i, :len(text)] = [idx for idx in text]
    #new_texts = np.split(new_texts, 2)
    new_texts = new_texts[:evaluate_wav_num]
    half_size = int(len(fpaths)/2)
    print(half_size)
    #new_fpaths = [fpaths[:half_size], fpaths[half_size:]]
    fpaths = fpaths[:evaluate_wav_num]
    saver = tf.train.Saver()
    with tf.Session() as sess:
        saver.restore(sess, tf.train.latest_checkpoint(hp.logdir)); print("Evaluate Model Restored!")
        """
        err = 0.0

        for i, t_split in enumerate(new_texts):
            y_hat = np.zeros((t_split.shape[0], 200, hp.n_mels*hp.r), np.float32)  # hp.n_mels*hp.r
            for j in tqdm.tqdm(range(200)):
                _y_hat = sess.run(g.y_hat, {g.x: t_split, g.y: y_hat})
                y_hat[:, j, :] = _y_hat[:, j, :]

            mags = sess.run(g.z_hat, {g.y_hat: y_hat})
            for k, mag in enumerate(mags):
                fname, mel_ans, mag_ans = load_spectrograms(new_fpaths[i][k])
                print("File {} is being evaluated ...".format(fname))
                audio = spectrogram2wav(mag)
                audio_ans = spectrogram2wav(mag_ans)
                err += calculate_mse(audio, audio_ans)

        err = err/float(len(fpaths))
        print(err)

        """
        # Feed Forward
        ## mel
        y_hat = np.zeros((new_texts.shape[0], 200, hp.n_mels*hp.r), np.float32)  # hp.n_mels*hp.r
        for j in tqdm.tqdm(range(200)):
            _y_hat = sess.run(g.y_hat, {g.x: new_texts, g.y: y_hat})
            y_hat[:, j, :] = _y_hat[:, j, :]
        ## mag
        mags = sess.run(g.z_hat, {g.y_hat: y_hat})
        err = 0.0
        for i, mag in enumerate(mags):
            fname, mel_ans, mag_ans = load_spectrograms(fpaths[i])
            print("File {} is being evaluated ...".format(fname))
            #audio = spectrogram2wav(mag)
            #audio_ans = spectrogram2wav(mag_ans)
            #err += calculate_mse(audio, audio_ans)
            err += calculate_mse(mag, mag_ans)
        err = err/float(len(fpaths))
        print(err)
        opf.write(hp.logdir  + " spectrogram mse: " + str(err) + "\n")