fastapi client bugfix for static noise and load balancing for coqui e…

…ngine

.gitignore

@@ -1 +1,175 @@
+.gitignore
+_open_cmd.bat
+docs/
+examples/
+batch/
+test_env/
+tests_private/
+docs/
+docs_private/
+env_realtimetts/
+example_rvc/assets/
+server/
+RealtimeTTS.code-workspace
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+myenv/
 venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

RealtimeTTS/engines/coqui_engine.py

@@ -79,6 +79,9 @@ def __init__(
         sentence_silence_duration=0.6,
         default_silence_duration=0.3,
         print_realtime_factor=False,
+        load_balancing=False,
+        load_balancing_buffer_length=0,
+        load_balancing_cut_off=0,
     ):
         """
         Initializes a coqui voice realtime text to speech engine object.
@@ -140,6 +143,16 @@ def __init__(
               Duration of the silence after a comma.
             sentence_silence_duration (float):
               Duration of the silence after a sentence.
+            default_silence_duration (float):
+                Default duration of the silence.
+            print_realtime_factor (bool):
+                Print the realtime factor for the coqui model.
+            load_balancing (bool):
+                Enable load balancing for the coqui model.
+            load_balancing_buffer_length (int):
+                Buffer length for the load balancing.
+            load_balancing_cut_off (int):
+                Cut off for the load balancing.
         """
 
         self._synthesize_lock = Lock()
@@ -164,6 +177,9 @@ def __init__(
         self.sentence_silence_duration = sentence_silence_duration
         self.default_silence_duration = default_silence_duration
         self.print_realtime_factor = print_realtime_factor
+        self.load_balancing = load_balancing
+        self.load_balancing_buffer_length = load_balancing_buffer_length
+        self.load_balancing_cut_off = load_balancing_cut_off
 
         self.cloning_reference_wav = voice
         self.speed = speed
@@ -261,6 +277,9 @@ def output_worker(queue):
                 self.sentence_silence_duration,
                 self.default_silence_duration,
                 self.print_realtime_factor,
+                self.load_balancing,
+                self.load_balancing_buffer_length,
+                self.load_balancing_cut_off,
             ),
         )
         self.synthesize_process.start()
@@ -302,6 +321,9 @@ def _synthesize_worker(
         sentence_silence_duration,
         default_silence_duration,
         print_realtime_factor,
+        load_balancing,
+        load_balancing_buffer_length,
+        load_balancing_cut_off,
     ):
         """
         Worker process for the coqui text to speech synthesis model.
@@ -612,17 +634,8 @@ def get_user_data_dir(appname):
                         continue
                 else:
                     # Poll timed out, continue without blocking
-                    time.sleep(0.01)  # You can adjust this sleep to fit your needs
+                    time.sleep(0.01)
                     continue
-                # try:
-                #     message = conn.recv()
-                # except Exception as e:
-                #     logging.error(
-                #         f"conn.recv() error: {e} occured in "
-                #         "synthesize worker thread of coqui engine."
-                #     )
-                #     time.sleep(1)
-                #     continue
 
                 command = message["command"]
                 data = message["data"]
@@ -715,6 +728,18 @@ def get_user_data_dir(appname):
                                 seconds_to_first_chunk = (
                                     raw_inference_start - time_start
                                 )
+                            else:
+                                chunk_production_seconds = time.time() - time_start
+                                generated_audio_seconds = full_generated_seconds
+
+                                # wait only if we are faster than realtime, meaning
+                                # that chunk_production_seconds is smaller than generated_audio_seconds
+                                if load_balancing:
+                                    if chunk_production_seconds < (generated_audio_seconds + load_balancing_buffer_length):
+                                        waiting_time = generated_audio_seconds - chunk_production_seconds - load_balancing_cut_off
+                                        if waiting_time > 0:
+                                            print(f"Waiting for {waiting_time} seconds")
+                                            time.sleep(waiting_time)
 
                     time_end = time.time()
                     seconds = time_end - time_start
@@ -732,6 +757,7 @@ def get_user_data_dir(appname):
                             print(f"Realtime Factor: {realtime_factor}")
                             print(f"Raw Inference Factor: {raw_inference_factor}")
 
+
                     # Send silent audio
                     sample_rate = config.audio.sample_rate
 
@@ -751,6 +777,8 @@ def get_user_data_dir(appname):
 
                     conn.send(("finished", ""))
 
+                    end_time = time.time()
+
         except KeyboardInterrupt:
             logging.info("Keyboard interrupt received. " "Exiting worker process.")
             conn.send(("shutdown", "shutdown"))