Adding versioning in a file

MANIFEST.in

@@ -3,6 +3,7 @@ include LICENSE.txt
 include requirements.*.txt
 include *.cff
 include requirements.txt
+include matcha/VERSION
 recursive-include matcha *.json
 recursive-include matcha *.html
 recursive-include matcha *.png

README.md

@@ -28,6 +28,8 @@ We propose 🍵 Matcha-TTS, a new approach to non-autoregressive neural TTS, tha
 
 Check out our [demo page](https://shivammehta25.github.io/Matcha-TTS). Read our [arXiv preprint for more details](https://arxiv.org/abs/2309.03199).
 
+[Pretrained models](https://drive.google.com/drive/folders/17C_gYgEHOxI5ZypcfE_k1piKCtyR0isJ?usp=sharing) will be auto downloaded with the CLI or gradio interface.
+
 <br>
 
 ## Installation
@@ -35,8 +37,8 @@ Check out our [demo page](https://shivammehta25.github.io/Matcha-TTS). Read our
 1. Create an environment (suggested but optional)
 
 ```
-conda create -n matcha_tts python=3.10 -y
+conda create -n matcha-tts python=3.10 -y
-conda activate matcha_tts
+conda activate matcha-tts
 ```
 
 2. Install Matcha TTS using pip from source
@@ -50,13 +52,13 @@ pip install git+https://github.com/shivammehta25/Matcha-TTS.git
 
 ```bash
 # This will download the required models
-match_tts --text "<INPUT TEXT>"
+matcha-tts --text "<INPUT TEXT>"
 ```
 
 or
 
 ```bash
-matcha_tts_app
+matcha-tts_app
 ```
 
 or open `synthesis.ipynb` on jupyter notebook
@@ -66,19 +68,19 @@ or open `synthesis.ipynb` on jupyter notebook
 - To synthesise from given text, run:
 
 ```bash
-match_tts --text "<INPUT TEXT>"
+matcha-tts --text "<INPUT TEXT>"
 ```
 
 - To synthesise from a file, run:
 
 ```bash
-match_tts --file <PATH TO FILE>
+matcha-tts --file <PATH TO FILE>
 ```
 
 - To batch synthesise from a file, run:
 
 ```bash
-match_tts --file <PATH TO FILE> --batched
+matcha-tts --file <PATH TO FILE> --batched
 ```
 
 Additional arguments
@@ -86,19 +88,19 @@ Additional arguments
 - Speaking rate
 
 ```bash
-match_tts --text "<INPUT TEXT>" --speaking_rate 1.0
+matcha-tts --text "<INPUT TEXT>" --speaking_rate 1.0
 ```
 
 - Sampling temperature
 
 ```bash
-match_tts --text "<INPUT TEXT>" --temperature 0.667
+matcha-tts --text "<INPUT TEXT>" --temperature 0.667
 ```
 
 - Euler ODE solver steps
 
 ```bash
-match_tts --text "<INPUT TEXT>" --steps 10
+matcha-tts --text "<INPUT TEXT>" --steps 10
 ```
 
 ## Citation information
@@ -185,7 +187,7 @@ python matcha/train.py experiment=ljspeech trainer.devices=[0,1]
 6. Synthesise from the custom trained model
 
 ```bash
-matcha_tts --text "<INPUT TEXT>" --checkpoint_path <PATH TO CHECKPOINT>
+matcha-tts --text "<INPUT TEXT>" --checkpoint_path <PATH TO CHECKPOINT>
 ```
 
 ## Acknowledgements

matcha/VERSION

@@ -0,0 +1 @@
+0.0.1.dev0

matcha/app.py

@@ -30,7 +30,7 @@ args = Namespace(
 MATCHA_TTS_LOC = LOCATION / f"{args.model}.ckpt"
 VOCODER_LOC = LOCATION / f"{args.vocoder}"
 LOGO_URL = "https://shivammehta25.github.io/Matcha-TTS/images/logo.png"
-assert_model_downloaded(MATCHA_TTS_LOC, MATCHA_URLS[args.model], use_wget=True)
+assert_model_downloaded(MATCHA_TTS_LOC, MATCHA_URLS[args.model])
 assert_model_downloaded(VOCODER_LOC, VOCODER_URL[args.vocoder])
 device = get_device(args)
 

matcha/cli.py

@@ -16,14 +16,14 @@ 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, intersperse
 
-MATCHA_URLS = {"matcha_ljspeech": ""}  # , "matcha_vctk": ""}  # Coming soon
+MATCHA_URLS = {
+    "matcha_ljspeech": "https://drive.google.com/file/d/1BBzmMU7k3a_WetDfaFblMoN18GqQeHCg/view?usp=drive_link"
+}  # , "matcha_vctk": ""}  # Coming soon
 
 MULTISPEAKER_MODEL = {"matcha_vctk"}
 SINGLESPEAKER_MODEL = {"matcha_ljspeech"}
 
-VOCODER_URL = {
+VOCODER_URL = {"hifigan_T2_v1": "https://drive.google.com/file/d/14NENd4equCBLyyCSke114Mv6YR_j_uFs/view?usp=drive_link"}
-    "hifigan_T2_v1": "https://drive.google.com/file/d/14NENd4equCBLyyCSke114Mv6YR_j_uFs/view?usp=drive_link",
-}
 
 
 def plot_spectrogram_to_numpy(spectrogram, filename):
@@ -64,7 +64,7 @@ def assert_required_models_available(args):
     save_dir = get_user_data_dir()
     model_path = save_dir / f"{args.model}.ckpt"
     vocoder_path = save_dir / f"{args.vocoder}"
-    assert_model_downloaded(model_path, MATCHA_URLS[args.model], use_wget=True)
+    assert_model_downloaded(model_path, MATCHA_URLS[args.model])
     assert_model_downloaded(vocoder_path, VOCODER_URL[args.vocoder])
     return {"matcha": model_path, "vocoder": vocoder_path}
 

setup.py

@@ -15,10 +15,13 @@ exts = [
 with open("README.md", encoding="utf-8") as readme_file:
     README = readme_file.read()
 
+cwd = os.path.dirname(os.path.abspath(__file__))
+with open(os.path.join(cwd, "matcha", "VERSION")) as fin:
+    version = fin.read().strip()
 
 setup(
     name="matcha-tts",
-    version="0.0.0.1.dev0",
+    version=version,
     description="🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching",
     long_description=README,
     long_description_content_type="text/markdown",