Ensure `tts` CLI tool readme and usage help is in sync

README.md

@@ -294,6 +294,15 @@ api.tts_with_vc_to_file(
 ```
 
 ### Command-line `tts`
+
+<!-- begin-tts-readme -->
+
+Synthesize speech on command line.
+
+You can either use your trained model or choose a model from the provided list.
+
+If you don't specify any models, then it uses LJSpeech based English model.
+
 #### Single Speaker Models
 
 - List provided models:
@@ -301,31 +310,37 @@ api.tts_with_vc_to_file(
   ```
   $ tts --list_models
   ```
+
 - Get model info (for both tts_models and vocoder_models):
+
   - Query by type/name:
     The model_info_by_name uses the name as it from the --list_models.
     ```
     $ tts --model_info_by_name "<model_type>/<language>/<dataset>/<model_name>"
     ```
     For example:
-
     ```
     $ tts --model_info_by_name tts_models/tr/common-voice/glow-tts
-        ```
-        ```
     $ tts --model_info_by_name vocoder_models/en/ljspeech/hifigan_v2
     ```
   - Query by type/idx:
     The model_query_idx uses the corresponding idx from --list_models.
+
     ```
     $ tts --model_info_by_idx "<model_type>/<model_query_idx>"
     ```
+
     For example:
 
     ```
     $ tts --model_info_by_idx tts_models/3
     ```
 
+  - Query info for model info by full name:
+    ```
+    $ tts --model_info_by_name "<model_type>/<language>/<dataset>/<model_name>"
+    ```
+
 - Run TTS with default models:
 
   ```
@@ -337,6 +352,7 @@ api.tts_with_vc_to_file(
   ```
   $ tts --text "Text for TTS" --model_name "<model_type>/<language>/<dataset>/<model_name>" --out_path output/path/speech.wav
   ```
+
   For example:
 
   ```
@@ -355,7 +371,6 @@ api.tts_with_vc_to_file(
   $ tts --text "Text for TTS" --model_name "tts_models/en/ljspeech/glow-tts" --vocoder_name "vocoder_models/en/ljspeech/univnet" --out_path output/path/speech.wav
   ```
 
-
 - Run your own TTS model (Using Griffin-Lim Vocoder):
 
   ```
@@ -363,6 +378,7 @@ api.tts_with_vc_to_file(
   ```
 
 - Run your own TTS and Vocoder models:
+
   ```
   $ tts --text "Text for TTS" --model_path path/to/model.pth --config_path path/to/config.json --out_path output/path/speech.wav
       --vocoder_path path/to/vocoder.pth --vocoder_config_path path/to/vocoder_config.json
@@ -388,6 +404,14 @@ api.tts_with_vc_to_file(
   $ tts --text "Text for TTS" --out_path output/path/speech.wav --model_path path/to/model.pth --config_path path/to/config.json --speakers_file_path path/to/speaker.json --speaker_idx <speaker_id>
   ```
 
+### Voice Conversion Models
+
+```
+$ tts --out_path output/path/speech.wav --model_name "<language>/<dataset>/<model_name>" --source_wav <path/to/speaker/wav> --target_wav <path/to/reference/wav>
+```
+
+<!-- end-tts-readme -->
+
 ## Directory Structure
 ```
 |- notebooks/       (Jupyter Notebooks for model evaluation, parameter selection and data analysis.)

TTS/bin/synthesize.py

@@ -12,27 +12,14 @@ from TTS.api import TTS
 from TTS.utils.manage import ModelManager
 from TTS.utils.synthesizer import Synthesizer
 
-
+description = """
-def str2bool(v):
+Synthesize speech on command line.
-    if isinstance(v, bool):
-        return v
-    if v.lower() in ("yes", "true", "t", "y", "1"):
-        return True
-    if v.lower() in ("no", "false", "f", "n", "0"):
-        return False
-    raise argparse.ArgumentTypeError("Boolean value expected.")
-
-
-def main():
-    description = """Synthesize speech on command line.
 
 You can either use your trained model or choose a model from the provided list.
 
 If you don't specify any models, then it uses LJSpeech based English model.
 
-## Example Runs
+#### Single Speaker Models
-
-### Single Speaker Models
 
 - List provided models:
 
@@ -40,14 +27,32 @@ If you don't specify any models, then it uses LJSpeech based English model.
   $ tts --list_models
   ```
 
-- Query info for model info by idx:
+- Get model info (for both tts_models and vocoder_models):
+
+  - Query by type/name:
+    The model_info_by_name uses the name as it from the --list_models.
+    ```
+    $ tts --model_info_by_name "<model_type>/<language>/<dataset>/<model_name>"
+    ```
+    For example:
+    ```
+    $ tts --model_info_by_name tts_models/tr/common-voice/glow-tts
+    $ tts --model_info_by_name vocoder_models/en/ljspeech/hifigan_v2
+    ```
+  - Query by type/idx:
+    The model_query_idx uses the corresponding idx from --list_models.
 
     ```
     $ tts --model_info_by_idx "<model_type>/<model_query_idx>"
     ```
 
-- Query info for model info by full name:
+    For example:
 
+    ```
+    $ tts --model_info_by_idx tts_models/3
+    ```
+
+  - Query info for model info by full name:
     ```
     $ tts --model_info_by_name "<model_type>/<language>/<dataset>/<model_name>"
     ```
@@ -55,19 +60,31 @@ If you don't specify any models, then it uses LJSpeech based English model.
 - Run TTS with default models:
 
   ```
-    $ tts --text "Text for TTS"
+  $ tts --text "Text for TTS" --out_path output/path/speech.wav
   ```
 
 - Run a TTS model with its default vocoder model:
 
   ```
-    $ tts --text "Text for TTS" --model_name "<model_type>/<language>/<dataset>/<model_name>
+  $ tts --text "Text for TTS" --model_name "<model_type>/<language>/<dataset>/<model_name>" --out_path output/path/speech.wav
+  ```
+
+  For example:
+
+  ```
+  $ tts --text "Text for TTS" --model_name "tts_models/en/ljspeech/glow-tts" --out_path output/path/speech.wav
   ```
 
 - Run with specific TTS and vocoder models from the list:
 
   ```
-    $ tts --text "Text for TTS" --model_name "<model_type>/<language>/<dataset>/<model_name>" --vocoder_name "<model_type>/<language>/<dataset>/<model_name>" --output_path
+  $ tts --text "Text for TTS" --model_name "<model_type>/<language>/<dataset>/<model_name>" --vocoder_name "<model_type>/<language>/<dataset>/<model_name>" --out_path output/path/speech.wav
+  ```
+
+  For example:
+
+  ```
+  $ tts --text "Text for TTS" --model_name "tts_models/en/ljspeech/glow-tts" --vocoder_name "vocoder_models/en/ljspeech/univnet" --out_path output/path/speech.wav
   ```
 
 - Run your own TTS model (Using Griffin-Lim Vocoder):
@@ -77,14 +94,15 @@ If you don't specify any models, then it uses LJSpeech based English model.
   ```
 
 - Run your own TTS and Vocoder models:
+
   ```
-    $ tts --text "Text for TTS" --model_path path/to/config.json --config_path path/to/model.pth --out_path output/path/speech.wav
+  $ tts --text "Text for TTS" --model_path path/to/model.pth --config_path path/to/config.json --out_path output/path/speech.wav
       --vocoder_path path/to/vocoder.pth --vocoder_config_path path/to/vocoder_config.json
   ```
 
-### Multi-speaker Models
+#### Multi-speaker Models
 
-- List the available speakers and choose as <speaker_id> among them:
+- List the available speakers and choose a <speaker_id> among them:
 
   ```
   $ tts --model_name "<language>/<dataset>/<model_name>"  --list_speaker_idxs
@@ -99,7 +117,7 @@ If you don't specify any models, then it uses LJSpeech based English model.
 - Run your own multi-speaker TTS model:
 
   ```
-    $ tts --text "Text for TTS" --out_path output/path/speech.wav --model_path path/to/config.json --config_path path/to/model.pth --speakers_file_path path/to/speaker.json --speaker_idx <speaker_id>
+  $ tts --text "Text for TTS" --out_path output/path/speech.wav --model_path path/to/model.pth --config_path path/to/config.json --speakers_file_path path/to/speaker.json --speaker_idx <speaker_id>
   ```
 
 ### Voice Conversion Models
@@ -108,8 +126,19 @@ If you don't specify any models, then it uses LJSpeech based English model.
 $ tts --out_path output/path/speech.wav --model_name "<language>/<dataset>/<model_name>" --source_wav <path/to/speaker/wav> --target_wav <path/to/reference/wav>
 ```
 """
-    # We remove Markdown code formatting programmatically here to allow us to copy-and-paste from main README to keep
+
-    # documentation in sync more easily.
+
+def str2bool(v):
+    if isinstance(v, bool):
+        return v
+    if v.lower() in ("yes", "true", "t", "y", "1"):
+        return True
+    if v.lower() in ("no", "false", "f", "n", "0"):
+        return False
+    raise argparse.ArgumentTypeError("Boolean value expected.")
+
+
+def main():
     parser = argparse.ArgumentParser(
         description=description.replace("    ```\n", ""),
         formatter_class=RawTextHelpFormatter,

scripts/sync_readme.py

@@ -0,0 +1,32 @@
+import argparse
+from pathlib import Path
+
+
+def replace_between_markers(content, marker: str, replacement: str) -> str:
+    start_marker = f"<!-- begin-{marker} -->\n\n"
+    end_marker = f"\n\n<!-- end-{marker} -->\n"
+    start_index = content.index(start_marker) + len(start_marker)
+    end_index = content.index(end_marker)
+    content = content[:start_index] + replacement + content[end_index:]
+    return content
+
+
+def sync_readme():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--check", action="store_true", default=False)
+    args = ap.parse_args()
+    readme_path = Path(__file__).parent.parent / "README.md"
+    orig_content = readme_path.read_text()
+    from TTS.bin.synthesize import description
+
+    new_content = replace_between_markers(orig_content, "tts-readme", description.strip())
+    if args.check:
+        if orig_content != new_content:
+            print("README.md is out of sync; please edit TTS/bin/TTS_README.md and run scripts/sync_readme.py")
+            exit(42)
+    readme_path.write_text(new_content)
+    print("Updated README.md")
+
+
+if __name__ == "__main__":
+    sync_readme()

tests/aux_tests/test_readme.py

@@ -0,0 +1,9 @@
+import subprocess
+import sys
+from pathlib import Path
+
+
+def test_readme_up_to_date():
+    root = Path(__file__).parent.parent.parent
+    sync_readme = root / "scripts" / "sync_readme.py"
+    subprocess.check_call([sys.executable, str(sync_readme), "--check"], cwd=root)