initial commit intro. to vocoder submodule

2026-09-20 12:30:22 +08:00 · 2020-05-30 18:09:25 +02:00
parent 4ecd47e072
commit d47c9987db
35 changed files with 3737 additions and 0 deletions
@@ -0,0 +1,102 @@
+import re
+import importlib
+import numpy as np
+from matplotlib import pyplot as plt
+
+from TTS.utils.visual import plot_spectrogram
+
+
+def plot_results(y_hat, y, ap, global_step, name_prefix):
+    """ Plot vocoder model results """
+
+    # select an instance from batch
+    y_hat = y_hat[0].squeeze(0).detach().cpu().numpy()
+    y = y[0].squeeze(0).detach().cpu().numpy()
+
+    spec_fake = ap.spectrogram(y_hat).T
+    spec_real = ap.spectrogram(y).T
+    spec_diff = np.abs(spec_fake - spec_real)
+
+    # plot figure and save it
+    fig_wave = plt.figure()
+    plt.subplot(2, 1, 1)
+    plt.plot(y)
+    plt.title("groundtruth speech")
+    plt.subplot(2, 1, 2)
+    plt.plot(y_hat)
+    plt.title(f"generated speech @ {global_step} steps")
+    plt.tight_layout()
+    plt.close()
+
+    figures = {
+        name_prefix + "/spectrogram/fake": plot_spectrogram(spec_fake, ap),
+        name_prefix + "spectrogram/real": plot_spectrogram(spec_real, ap),
+        name_prefix + "spectrogram/diff": plot_spectrogram(spec_diff, ap),
+        name_prefix + "speech_comparison": fig_wave,
+    }
+    return figures
+
+
+def to_camel(text):
+    text = text.capitalize()
+    return re.sub(r'(?!^)_([a-zA-Z])', lambda m: m.group(1).upper(), text)
+
+
+def setup_generator(c):
+    print(" > Generator Model: {}".format(c.generator_model))
+    MyModel = importlib.import_module('TTS.vocoder.models.' +
+                                      c.generator_model.lower())
+    MyModel = getattr(MyModel, to_camel(c.generator_model))
+    if c.generator_model in 'melgan_generator':
+        model = MyModel(
+            in_channels=c.audio['num_mels'],
+            out_channels=1,
+            proj_kernel=7,
+            base_channels=512,
+            upsample_factors=c.generator_model_params['upsample_factors'],
+            res_kernel=3,
+            num_res_blocks=c.generator_model_params['num_res_blocks'])
+    if c.generator_model in 'melgan_fb_generator':
+        pass
+    if c.generator_model in 'multiband_melgan_generator':
+        model = MyModel(
+            in_channels=c.audio['num_mels'],
+            out_channels=4,
+            proj_kernel=7,
+            base_channels=384,
+            upsample_factors=c.generator_model_params['upsample_factors'],
+            res_kernel=3,
+            num_res_blocks=c.generator_model_params['num_res_blocks'])
+    return model
+
+
+def setup_discriminator(c):
+    print(" > Discriminator Model: {}".format(c.discriminator_model))
+    MyModel = importlib.import_module('TTS.vocoder.models.' +
+                                      c.discriminator_model.lower())
+    MyModel = getattr(MyModel, to_camel(c.discriminator_model))
+    if c.discriminator_model in 'random_window_discriminator':
+        model = MyModel(
+            cond_channels=c.audio['num_mels'],
+            hop_length=c.audio['hop_length'],
+            uncond_disc_donwsample_factors=c.
+            discriminator_model_params['uncond_disc_donwsample_factors'],
+            cond_disc_downsample_factors=c.
+            discriminator_model_params['cond_disc_downsample_factors'],
+            cond_disc_out_channels=c.
+            discriminator_model_params['cond_disc_out_channels'],
+            window_sizes=c.discriminator_model_params['window_sizes'])
+    if c.discriminator_model in 'melgan_multiscale_discriminator':
+        model = MyModel(
+            in_channels=1,
+            out_channels=1,
+            kernel_sizes=(5, 3),
+            base_channels=c.discriminator_model_params['base_channels'],
+            max_channels=c.discriminator_model_params['max_channels'],
+            downsample_factors=c.
+            discriminator_model_params['downsample_factors'])
+    return model
+
+
+# def check_config(c):
+#     pass