Merge mimic3-client into main CLI

.dockerignore

@@ -3,7 +3,6 @@
 !install.sh
 !pyinstaller/*.py
 !pyinstaller/mimic3-server
-!pyinstaller/mimic3-client
 !pyinstaller/mimic3-download
 
 # opentts-abc

Dockerfile.binary

@@ -94,7 +94,6 @@ RUN find dist/mimic3/ -wholename '*/gruut_lang_*/espeak' -type d | \
 
 # Copy convenience scripts
 COPY pyinstaller/mimic3-server \
-    pyinstaller/mimic3-client \
     pyinstaller/mimic3-download \
     dist/mimic3/
 

README.md

@@ -76,7 +76,6 @@ pip install mimic3-http[all]
 
 Once installed, the following commands will be available:
     * `mimic3-server`
-    * `mimic3-client`
 
 Language support can be selectively installed by replacing `all` with:
 
@@ -111,7 +110,6 @@ A virtual environment will be created in `mimic3/.venv` and each of the Python m
 Once installed, the following commands will be available in `.venv/bin`:
     * `mimic3`
     * `mimic3-server`
-    * `mimic3-client`
     * `mimic3-download`
 
 
@@ -185,15 +183,17 @@ See `mimic3-server --help` for the [web server documentation](mimic3-http/) for
 
 #### Web Client
 
-The `mimic3-client` program provides an interface to the Mimic 3 web server that is similar to the `mimic3` command.
+The `mimic3` program provides an interface to the Mimic 3 web server when the `--remote` option is given.
 
 Assuming you have started `mimic3-server` and can access `http://localhost:59125`, then:
 
 ``` sh
-mimic3-client --voice 'en_UK/apope_low' 'My hovercraft is full of eels.' > hovercraft_eels.wav
+mimic3 --remote --voice 'en_UK/apope_low' 'My hovercraft is full of eels.' > hovercraft_eels.wav
 ```
 
-See `mimic3-client --help` for more options.
+If your server is somewhere besides `localhost`, use `mimic3 --remote <URL> ...`
+
+See `mimic3 --help` for more options.
 
 
 ## CUDA Acceleration

docker/mimic3-client

@@ -1,82 +0,0 @@
-#!/usr/bin/env bash
-# Copyright 2022 Mycroft AI Inc.
-#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-#
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-# Run mimic3-client --update to update Docker image
-
-args=()
-repo='mycroftai/mimic3'
-tag='latest'
-docker='docker'
-port='59125'
-
-while [[ -n "$1" ]]; do
-    if [[ "$1" == '--update' ]]; then
-        # Update Docker image
-        update='1'
-    elif [[ "$1" == '--port' ]]; then
-        port="$2"
-        args+=('--port' "${port}")
-        shift 1
-    else
-        args+=("$1")
-    fi
-
-    shift 1
-done
-
-if [[ -n "${update}" ]]; then
-    docker pull "${repo}:${tag}"
-fi
-
-docker_run_args=()
-
-if [[ -d /etc/ssl/certs ]]; then
-    # This directory seems to usually have symlinks to other directories
-    docker_run_args+=('-v' '/etc/ssl/certs:/etc/ssl/certs:ro')
-
-    # Create temp file with all certificate directories found
-    cert_dirs_file="$(mktemp)"
-    function finish {
-        rm -rf "${cert_dirs_file}"
-    }
-    trap finish EXIT
-
-    while read -r cert_path; do
-        # Follow symlinks and record directory paths
-        cert_path="$(readlink -f "${cert_path}")"
-        cert_dir="$(dirname "${cert_path}")"
-        echo $cert_dir >> "${cert_dirs_file}"
-    done < <(find /etc/ssl/certs -name '*.pem' -type l)
-
-    # Map unique certificate directories
-    while read -r cert_dir; do
-        docker_run_args+=('-v' "${cert_dir}:${cert_dir}:ro")
-    done < <(sort < "${cert_dirs_file}" | uniq)
-fi
-
-"${docker}" run \
-            -i \
-            --network host \
-            -e "HOME=${HOME}" \
-            -v "$HOME:${HOME}" \
-            -w "${PWD}" \
-            --user "$(id -u):$(id -g)" "${docker_run_args[@]}" \
-            --entrypoint '/home/mimic3/app/.venv/bin/python3' \
-            "${repo}:${tag}" \
-            -m mimic3_http.client \
-            --stdout \
-            "${args[@]}"

examples/speech-dispatcher/mimic3-generic.conf

@@ -1,2 +1,2 @@
-GenericExecuteSynth "printf %s \'$DATA\' | /path/to/mimic3-client --voice \'$VOICE\'  --stdout | $PLAY_COMMAND"
+GenericExecuteSynth "printf %s \'$DATA\' | /path/to/mimic3 --remote --voice \'$VOICE\'  --stdout | $PLAY_COMMAND"
 AddVoice "en-us" "MALE1" "en_UK/apope_low"

mimic3-http/README.md

@@ -42,10 +42,12 @@ Using [nvidia-docker](https://github.com/NVIDIA/nvidia-docker) is highly recomme
 Assuming you have started `mimic3-server` and can access `http://localhost:59125`, then:
 
 ``` sh
-mimic3-client --voice 'en_UK/apope_low' 'My hovercraft is full of eels.' > hovercraft_eels.wav
+mimic3 --remote --voice 'en_UK/apope_low' 'My hovercraft is full of eels.' > hovercraft_eels.wav
 ```
 
-See `mimic3-client --help` for more options.
+If your server is somewhere besides `localhost`, use `mimic3 --remote <URL> ...`
+
+See `mimic3 --help` for more options.
 
 
 ## MaryTTS Compatibility

mimic3-http/mimic3_http/app.py

@@ -26,7 +26,7 @@ from urllib.parse import parse_qs
 from uuid import uuid4
 
 import quart_cors
-from mimic3_tts import Mimic3Settings, Mimic3TextToSpeechSystem
+from mimic3_tts import DEFAULT_VOICE, Mimic3Settings, Mimic3TextToSpeechSystem
 from quart import (
     Quart,
     Response,
@@ -159,9 +159,8 @@ def get_app(args: argparse.Namespace, request_queue: Queue, temp_dir: str):
 
         _LOGGER.debug("Request args: %s", request.args)
 
-        voice = request.args.get("voice")
+        voice = request.args.get("voice") or args.voice or DEFAULT_VOICE
-        if voice is not None:
+        tts_args["voice"] = str(voice)
-            tts_args["voice"] = str(voice)
 
         # TTS settings
         noise_scale = request.args.get("noiseScale")
@@ -226,7 +225,7 @@ def get_app(args: argparse.Namespace, request_queue: Queue, temp_dir: str):
             text = request.args.get("INPUT_TEXT", "")
             voice = str(request.args.get("VOICE", voice)).strip()
 
-        voice = voice or args.voice
+        voice = voice or args.voice or DEFAULT_VOICE
 
         # Assume SSML if text begins with an angle bracket
         ssml = text.strip().startswith("<")

mimic3-http/mimic3_http/client.py

@@ -1,175 +0,0 @@
-#!/usr/bin/env python3
-# Copyright 2022 Mycroft AI Inc.
-#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-#
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-import argparse
-import logging
-import os
-import shlex
-import shutil
-import subprocess
-import sys
-import tempfile
-import typing
-from pathlib import Path
-
-import requests
-
-_PACKAGE = "mimic3_http.client"
-
-_LOGGER = logging.getLogger(_PACKAGE)
-
-_DEFAULT_PLAY_PROGRAMS = ["paplay", "play -q", "aplay -q"]
-
-# -----------------------------------------------------------------------------
-
-
-def main(argv=None):
-    args = get_args(argv)
-
-    if args.output:
-        args.output = Path(args.output)
-        args.output.parent.mkdir(parents=True, exist_ok=True)
-
-    if args.ssml:
-        headers = {"Content-Type": "application/ssml+xml"}
-    else:
-        headers = {"Content-Type": "text/plain"}
-
-    params: typing.Dict[str, str] = {}
-
-    if args.voice:
-        params["voice"] = args.voice
-
-    if args.length_scale:
-        params["lengthScale"] = args.length_scale
-
-    if args.noise_scale:
-        params["noiseScale"] = args.noise_scale
-
-    if args.noise_w:
-        params["noiseW"] = args.noise_w
-
-    if args.text:
-        data = "\n".join(args.text)
-    else:
-        if os.isatty(sys.stdin.fileno()):
-            print("Reading text from stdin...", file=sys.stderr)
-
-        data = sys.stdin.read()
-
-    wav_bytes = requests.post(
-        args.url, headers=headers, params=params, data=data
-    ).content
-
-    if args.output:
-        args.output.write_bytes(wav_bytes)
-        _LOGGER.info("Wrote WAV data to %s", args.output)
-    elif args.stdout or (not sys.stdout.isatty()):
-        _LOGGER.debug("Writing WAV data to stdout")
-        sys.stdout.buffer.write(wav_bytes)
-    else:
-        play_wav_bytes(args, wav_bytes)
-
-
-# -----------------------------------------------------------------------------
-
-
-def play_wav_bytes(args: argparse.Namespace, wav_bytes: bytes):
-    with tempfile.NamedTemporaryFile(mode="wb+", suffix=".wav") as wav_file:
-        wav_file.write(wav_bytes)
-        wav_file.seek(0)
-
-        for play_program in reversed(args.play_program):
-            play_cmd = shlex.split(play_program)
-            if not shutil.which(play_cmd[0]):
-                continue
-
-            play_cmd.append(wav_file.name)
-            _LOGGER.debug("Playing WAV file: %s", play_cmd)
-            subprocess.check_output(play_cmd)
-            break
-
-
-# -----------------------------------------------------------------------------
-
-
-def get_args(argv) -> argparse.Namespace:
-    parser = argparse.ArgumentParser(
-        prog=_PACKAGE, description="Client for Mimic 3 HTTP web server"
-    )
-    parser.add_argument(
-        "text", nargs="*", help="Text to convert to speech (default: stdin)"
-    )
-    parser.add_argument(
-        "--url",
-        "-u",
-        default="http://localhost:59125/api/tts",
-        help="URL of mimic3 HTTP server (default: http://localhost:59125/api/tts)",
-    )
-    parser.add_argument(
-        "--voice",
-        "-v",
-        help="Name of voice (expected in <voices-dir>/<language>)",
-    )
-    parser.add_argument(
-        "--output",
-        "-o",
-        help="Path to write WAV file (default: play audio)",
-    )
-    parser.add_argument(
-        "--stdout",
-        action="store_true",
-        help="Write WAV data to stdout",
-    )
-    parser.add_argument(
-        "--noise-scale",
-        type=float,
-        help="Noise scale [0-1], default is 0.667",
-    )
-    parser.add_argument(
-        "--length-scale",
-        type=float,
-        help="Length scale (1.0 is default speed, 0.5 is 2x faster)",
-    )
-    parser.add_argument(
-        "--noise-w",
-        type=float,
-        help="Variation in cadence [0-1], default is 0.8",
-    )
-    parser.add_argument(
-        "--play-program",
-        action="append",
-        default=_DEFAULT_PLAY_PROGRAMS,
-        help="Program(s) used to play WAV files",
-    )
-    parser.add_argument("--ssml", action="store_true", help="Input text is SSML")
-    parser.add_argument(
-        "--debug", action="store_true", help="Print DEBUG messages to the console"
-    )
-    args = parser.parse_args(args=argv)
-
-    if args.debug:
-        logging.basicConfig(level=logging.DEBUG)
-    else:
-        logging.basicConfig(level=logging.INFO)
-
-    return args
-
-
-# -----------------------------------------------------------------------------
-
-if __name__ == "__main__":
-    main()

mimic3-http/mimic3_http/examples/speech-dispatcher/mimic3-generic.conf

@@ -1,2 +0,0 @@
-GenericExecuteSynth "printf %s \'$DATA\' | /home/hansenm/opt/mimic3/mimic3-http/client.sh --voice \'$VOICE\' --length-scale 0.5 --stdout | $PLAY_COMMAND"
-AddVoice "en-us" "FEMALE1" "en_US/amy_low"

mimic3-http/mimic3_http/examples/speech-dispatcher/speechd.conf

@@ -1,2 +0,0 @@
-DefaultVoiceType  "FEMALE1"
-DefaultModule mimic3-generic

mimic3-http/mypy.ini

@@ -1,11 +1,5 @@
 [mypy]
 
-[mypy-playsound.*]
-ignore_missing_imports = True
-
-[mypy-requests.*]
-ignore_missing_imports = True
-
 [mypy-setuptools.*]
 ignore_missing_imports = True
 

mimic3-http/requirements.txt

@@ -1,5 +1,4 @@
 mimic3-tts<1.0
 quart>=0.16,<1.0
 quart-cors
-requests>=2,<3
 swagger-ui-py>=21,<22

mimic3-http/setup.py

@@ -95,7 +95,6 @@ setup(
     entry_points={
         "console_scripts": [
             "mimic3-server = mimic3_http.__main__:main",
-            "mimic3-client = mimic3_http.client:main",
         ]
     },
     classifiers=[

mimic3-tts/README.md

@@ -214,11 +214,11 @@ sudo apt-get install speech-dispatcher
 Create the file `/etc/speech-dispatcher/modules/mimic3-generic.conf` with the contents:
 
 ``` text
-GenericExecuteSynth "printf %s \'$DATA\' | /path/to/mimic3-client --voice \'$VOICE\' --stdout | $PLAY_COMMAND"
+GenericExecuteSynth "printf %s \'$DATA\' | /path/to/mimic3 --remote --voice \'$VOICE\' --stdout | $PLAY_COMMAND"
 AddVoice "en-us" "MALE1" "en_UK/apope_low"
 ```
 
-You will need `sudo` access to do this. Make sure to change `/path/to/mimic3-client` to wherever you installed Mimic 3.
+You will need `sudo` access to do this. Make sure to change `/path/to/mimic3` to wherever you installed Mimic 3. Note that the `--remote` option is used to connect to a local Mimic 3 web server (use `--remote <URL>` if your server is somewhere besides `localhost`).
 
 To change the voice later, you only need to replace `en_UK/apope_low`.
 

mimic3-tts/mimic3_tts/__init__.py

@@ -13,6 +13,7 @@ from opentts_abc import (
 from opentts_abc.ssml import SSMLSpeaker
 
 from ._resources import __version__
+from .const import DEFAULT_VOICE
 from .tts import Mimic3Settings, Mimic3TextToSpeechSystem
 
 __author__ = "Michael Hansen"

mimic3-tts/mimic3_tts/__main__.py

@@ -213,6 +213,14 @@ def initialize_args(state: CommandLineInterfaceState):
 
         state.texts = process_on_blank_line(state.texts)
 
+    if args.remote and args.remote.endswith("/"):
+        # Ensure no slash
+        args.remote = args.remote[:-1]
+
+    if (not args.speaker) and args.voice and ("#" in args.voice):
+        # Split apart voice
+        args.voice, args.speaker = args.voice.split("#", maxsplit=1)
+
 
 def initialize_tts(state: CommandLineInterfaceState):
     """Create Mimic 3 TTS from command-line arguments"""
@@ -220,24 +228,29 @@ def initialize_tts(state: CommandLineInterfaceState):
 
     args = state.args
 
-    state.tts = Mimic3TextToSpeechSystem(
+    if not args.remote:
-        Mimic3Settings(
+        # Local TTS
-            voices_directories=args.voices_dir, speaker=args.speaker, use_cuda=args.cuda
+        state.tts = Mimic3TextToSpeechSystem(
+            Mimic3Settings(
+                voices_directories=args.voices_dir,
+                speaker=args.speaker,
+                use_cuda=args.cuda,
+            )
         )
-    )
 
     if args.voices:
         # Don't bother with the rest of the initialization
         return
 
-    if state.args.voice:
+    if state.tts:
-        # Set default voice
+        if state.args.voice:
-        state.tts.voice = state.args.voice
+            # Set default voice
+            state.tts.voice = state.args.voice
 
-    if state.args.preload_voice:
+        if state.args.preload_voice:
-        for voice_key in state.args.preload_voice:
+            for voice_key in state.args.preload_voice:
-            _LOGGER.debug("Preloading voice: %s", voice_key)
+                _LOGGER.debug("Preloading voice: %s", voice_key)
-            state.tts.preload_voice(voice_key)
+                state.tts.preload_voice(voice_key)
 
     state.result_queue = Queue(maxsize=args.result_queue_size)
 
@@ -326,31 +339,52 @@ def process_line(
     line_id: str = "",
     line_voice: typing.Optional[str] = None,
 ):
-    from mimic3_tts import SSMLSpeaker
-
-    assert state.tts is not None
     assert state.result_queue is not None
 
-    args = state.args
+    if state.tts:
+        # Local TTS
+        from mimic3_tts import SSMLSpeaker
 
-    if line_voice:
+        assert state.tts is not None
-        if line_voice.startswith("#"):
+
-            # Same voice, but different speaker
+        args = state.args
-            state.tts.speaker = line_voice[1:]
+
+        if line_voice:
+            if line_voice.startswith("#"):
+                # Same voice, but different speaker
+                state.tts.speaker = line_voice[1:]
+            else:
+                # Different voice
+                state.tts.voice = line_voice
+
+        if args.ssml:
+            results = SSMLSpeaker(state.tts).speak(line)
         else:
-            # Different voice
+            state.tts.begin_utterance()
-            state.tts.voice = line_voice
 
-    if args.ssml:
+            # TODO: text language
-        results = SSMLSpeaker(state.tts).speak(line)
+            state.tts.speak_text(line)
+
+            results = state.tts.end_utterance()
     else:
-        state.tts.begin_utterance()
+        # Remote TTS
+        from mimic3_tts import AudioResult
 
-        # TODO: text language
+        # Get remote WAV data and repackage as AudioResult
-        state.tts.speak_text(line)
+        wav_bytes = get_remote_wav_bytes(state, line)
-
+        with io.BytesIO(wav_bytes) as wav_io:
-        results = state.tts.end_utterance()
+            wav_reader: wave.Wave_read = wave.open(wav_io, "rb")
+            with wav_reader as wav_file:
+                results = [
+                    AudioResult(
+                        sample_rate_hz=wav_file.getframerate(),
+                        sample_width_bytes=wav_file.getsampwidth(),
+                        num_channels=wav_file.getnchannels(),
+                        audio_bytes=wav_file.readframes(wav_file.getnframes()),
+                    )
+                ]
 
+    # Add results to processing queue
     for result in results:
         state.result_queue.put(
             ResultToProcess(
@@ -361,8 +395,9 @@ def process_line(
         )
 
     # Restore voice/speaker
-    state.tts.voice = args.voice
+    if state.tts:
-    state.tts.speaker = args.speaker
+        state.tts.voice = args.voice
+        state.tts.speaker = args.speaker
 
 
 def process_lines(state: CommandLineInterfaceState):
@@ -434,7 +469,7 @@ def process_lines(state: CommandLineInterfaceState):
 
 
 def shutdown_tts(state: CommandLineInterfaceState):
-    if state.tts is not None:
+    if state.tts:
         state.tts.shutdown()
         state.tts = None
 
@@ -456,10 +491,13 @@ def play_wav_bytes(args: argparse.Namespace, wav_bytes: bytes):
 
 
 def print_voices(state: CommandLineInterfaceState):
-    assert state.tts is not None
+    if state.tts:
-
+        # Local TTS
-    voices = list(state.tts.get_voices())
+        voices = list(state.tts.get_voices())
-    voices = sorted(voices, key=lambda v: v.key)
+        voices = sorted(voices, key=lambda v: v.key)
+    else:
+        # Remove TTS
+        voices = get_remote_voices(state)
 
     writer = csv.writer(sys.stdout, delimiter="\t")
     writer.writerow(("KEY", "LANGUAGE", "NAME", "DESCRIPTION", "LOCATION"))
@@ -472,6 +510,59 @@ def print_voices(state: CommandLineInterfaceState):
 # -----------------------------------------------------------------------------
 
 
+def get_remote_voices(state: CommandLineInterfaceState) -> typing.List:
+    import requests
+
+    from mimic3_tts import Voice
+
+    args = state.args
+
+    url = f"{args.remote}/api/voices"
+    _LOGGER.debug("Getting voices from remote server at %s", url)
+
+    voices_json = requests.get(url).json()
+
+    return [Voice(**voice_args) for voice_args in voices_json]
+
+
+def get_remote_wav_bytes(state: CommandLineInterfaceState, text: str) -> bytes:
+    import requests
+
+    args = state.args
+
+    if args.ssml:
+        headers = {"Content-Type": "application/ssml+xml"}
+    else:
+        headers = {"Content-Type": "text/plain"}
+
+    params: typing.Dict[str, str] = {}
+
+    if args.voice:
+        if args.speaker:
+            params["voice"] = f"{args.voice}#{args.speaker}"
+        else:
+            params["voice"] = args.voice
+
+    if args.length_scale:
+        params["lengthScale"] = args.length_scale
+
+    if args.noise_scale:
+        params["noiseScale"] = args.noise_scale
+
+    if args.noise_w:
+        params["noiseW"] = args.noise_w
+
+    url = f"{args.remote}/api/tts"
+    _LOGGER.debug("Synthesizing text remotely at %s", url)
+
+    wav_bytes = requests.post(url, headers=headers, params=params, data=text).content
+
+    return wav_bytes
+
+
+# -----------------------------------------------------------------------------
+
+
 def get_args(argv=None):
     """Parse command-line arguments"""
     parser = argparse.ArgumentParser(
@@ -480,6 +571,12 @@ def get_args(argv=None):
     parser.add_argument(
         "text", nargs="*", help="Text to convert to speech (default: stdin)"
     )
+    parser.add_argument(
+        "--remote",
+        nargs="?",
+        const="http://localhost:59125",
+        help="Connect to Mimic 3 HTTP web server for synthesis (default: localhost)",
+    )
     parser.add_argument(
         "--stdin-format",
         choices=[str(v.value) for v in StdinFormat],

mimic3-tts/mypy.ini

@@ -9,6 +9,9 @@ ignore_missing_imports = True
 [mypy-onnxruntime.*]
 ignore_missing_imports = True
 
+[mypy-requests.*]
+ignore_missing_imports = True
+
 [mypy-tqdm.*]
 ignore_missing_imports = True
 

mimic3-tts/requirements.txt

@@ -6,5 +6,6 @@ numpy<2.0
 onnxruntime>=1.6,<2.0
 opentts_abc<1.0
 phonemes2ids<2.0
+requests>=2,<3
 tqdm>=4,<5
 xdgenvpy>2.0,<3

pyinstaller/mimic3-client

@@ -1,25 +0,0 @@
-#!/usr/bin/env bash
-# Copyright 2022 Mycroft AI Inc.
-#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-#
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-# -----------------------------------------------------------------------------
-#
-# Stub script to execute web client in PyInstaller distribution.
-#
-
-# Directory of *this* script
-this_dir="$( cd "$( dirname "$0" )" && pwd )"
-
-"${this_dir}/mimic3" --subprogram client "$@"