Adding docstrings

matcha/app.py

@@ -6,9 +6,16 @@ import gradio as gr
 import soundfile as sf
 import torch
 
-from matcha.cli import (MATCHA_URLS, VOCODER_URL, assert_model_downloaded,
+from matcha.cli import (
-                        get_device, load_matcha, load_vocoder, process_text,
+    MATCHA_URLS,
-                        to_waveform)
+    VOCODER_URL,
+    assert_model_downloaded,
+    get_device,
+    load_matcha,
+    load_vocoder,
+    process_text,
+    to_waveform,
+)
 from matcha.utils.utils import get_user_data_dir, plot_tensor
 
 LOCATION = Path(get_user_data_dir())
@@ -59,6 +66,7 @@ def run_full_synthesis(text, n_timesteps, mel_temp, length_scale):
     audio, mel_spectrogram = synthesise_mel(text, text_lengths, n_timesteps, mel_temp, length_scale)
     return phones, audio, mel_spectrogram
 
+
 def main():
     description = """# 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
     ### [Shivam Mehta](https://www.kth.se/profile/smehta), [Ruibo Tu](https://www.kth.se/profile/ruibo), [Jonas Beskow](https://www.kth.se/profile/beskow), [Éva Székely](https://www.kth.se/profile/szekely), and [Gustav Eje Henter](https://people.kth.se/~ghe/)
@@ -80,7 +88,6 @@ def main():
     with gr.Blocks(title="🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching") as demo:
         processed_text = gr.State(value=None)
         processed_text_len = gr.State(value=None)
-        mel_variable = gr.State(value=None)
 
         with gr.Box():
             with gr.Row():
@@ -136,7 +143,7 @@ def main():
                 audio = gr.Audio(interactive=False, label="Audio")
 
         with gr.Row():
-            examples = gr.Examples(
+            examples = gr.Examples(  # pylint: disable=unused-variable
                 examples=[
                     [
                         "We propose Matcha-TTS, a new approach to non-autoregressive neural TTS, that uses conditional flow matching (similar to rectified flows) to speed up O D E-based speech synthesis.",
@@ -203,5 +210,6 @@ def main():
 
         demo.queue(concurrency_count=5).launch(share=True)
 
+
 if __name__ == "__main__":
     main()

matcha/cli.py

@@ -14,8 +14,7 @@ from matcha.hifigan.env import AttrDict
 from matcha.hifigan.models import Generator as HiFiGAN
 from matcha.models.matcha_tts import MatchaTTS
 from matcha.text import sequence_to_text, text_to_sequence
-from matcha.utils.utils import (assert_model_downloaded, get_user_data_dir,
+from matcha.utils.utils import assert_model_downloaded, get_user_data_dir, intersperse
-                                intersperse)
 
 MATCHA_URLS = {"matcha_ljspeech": ""}  # , "matcha_vctk": ""}  # Coming soon
 
@@ -146,7 +145,9 @@ def validate_args(args):
 
 @torch.inference_mode()
 def cli():
-    parser = argparse.ArgumentParser(description=" 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching")
+    parser = argparse.ArgumentParser(
+        description=" 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching"
+    )
     parser.add_argument(
         "--model",
         type=str,

matcha/models/components/decoder.py

@@ -69,6 +69,7 @@ class Downsample1D(nn.Module):
     def forward(self, x):
         return self.conv(x)
 
+
 class TimestepEmbedding(nn.Module):
     def __init__(
         self,
@@ -115,6 +116,7 @@ class TimestepEmbedding(nn.Module):
             sample = self.post_act(sample)
         return sample
 
+
 class Upsample1D(nn.Module):
     """A 1D upsampling layer with an optional convolution.
 

matcha/models/components/transformer.py

@@ -2,8 +2,13 @@ from typing import Any, Dict, Optional
 
 import torch
 import torch.nn as nn
-from diffusers.models.attention import (GEGLU, GELU, AdaLayerNorm,
+from diffusers.models.attention import (
-                                        AdaLayerNormZero, ApproximateGELU)
+    GEGLU,
+    GELU,
+    AdaLayerNorm,
+    AdaLayerNormZero,
+    ApproximateGELU,
+)
 from diffusers.models.attention_processor import Attention
 from diffusers.models.lora import LoRACompatibleLinear
 from diffusers.utils.torch_utils import maybe_allow_in_graph
@@ -38,7 +43,7 @@ class SnakeBeta(nn.Module):
             beta is initialized to 1 by default, higher values = higher-magnitude.
             alpha will be trained along with the rest of your model.
         """
-        super(SnakeBeta, self).__init__()
+        super().__init__()
         self.in_features = out_features if isinstance(out_features, list) else [out_features]
         self.proj = LoRACompatibleLinear(in_features, out_features)
 
@@ -129,7 +134,6 @@ class FeedForward(nn.Module):
         return hidden_states
 
 
-
 @maybe_allow_in_graph
 class BasicTransformerBlock(nn.Module):
     r"""

matcha/models/matcha_tts.py

@@ -9,9 +9,13 @@ from matcha import utils
 from matcha.models.baselightningmodule import BaseLightningClass
 from matcha.models.components.flow_matching import CFM
 from matcha.models.components.text_encoder import TextEncoder
-from matcha.utils.model import (denormalize, duration_loss,
+from matcha.utils.model import (
-                                fix_len_compatibility, generate_path,
+    denormalize,
-                                sequence_mask)
+    duration_loss,
+    fix_len_compatibility,
+    generate_path,
+    sequence_mask,
+)
 
 log = utils.get_pylogger(__name__)
 

setup.py

@@ -12,7 +12,7 @@ exts = [
     )
 ]
 
-with open("README.md", "r", encoding="utf-8") as readme_file:
+with open("README.md", encoding="utf-8") as readme_file:
     README = readme_file.read()
 
 
@@ -25,10 +25,7 @@ setup(
     author="Shivam Mehta",
     author_email="shivam.mehta25@gmail.com",
     url="https://shivammehta25.github.io/Matcha-TTS",
-    install_requires=[
+    install_requires=[str(r) for r in open(os.path.join(os.path.dirname(__file__), "requirements.txt"))],
-        str(r)
-        for r in open(os.path.join(os.path.dirname(__file__), "requirements.txt"))
-    ],
     include_dirs=[numpy.get_include()],
     include_package_data=True,
     packages=find_packages(exclude=["tests", "tests/*", "examples", "examples/*"]),
@@ -42,5 +39,4 @@ setup(
     },
     ext_modules=cythonize(exts, language_level=3),
     python_requires=">=3.9.0",
-
 )