Fix dictionary with multiple pronunciations

sed -i is not POSIX compliant, instead make a temp copy and rename to…

.dockerignore

@@ -1,26 +1,175 @@
-.git/
-.venv/
-node_modules/
-__pycache__/
-test/
-tools/
-etc/test/
-download/precise-engine/
-download/kaldi/
-opt/
+*
+!etc/qemu-*
 
-etc/homeassistant/config/.storage
-examples/typical/home-assistant/config/.storage
-examples/typical-intent/home-assistant/config/.storage
-examples/client-server/home-assistant/config/.storage
-examples/mqtt-hermes/home-assistant/config/.storage
+!download/rhasspy-tools*
+!download/pocketsphinx-python.tar.gz
+!download/snowboy*
+!download/kaldi*
 
-profiles/*/base_dictionary.txt
-profiles/*/base_language_model.txt
-profiles/*/acoustic_model/
-profiles/*/g2p.fst
+!requirements.txt
+!dist/
+!etc/wav
 
-profiles/en-kaldi/
-profiles/en-zamia/
+!docker/run.sh
+!docker/rhasspy
 
-profiles/*/download/
+!profiles/defaults.json
+
+!profiles/zh/profile.json
+!profiles/zh/custom_words.txt
+!profiles/zh/espeak_phonemes.txt
+!profiles/zh/phoneme_examples.txt
+!profiles/zh/frequent_words.txt
+!profiles/zh/sentences.ini
+!profiles/zh/stop_words.txt
+!profiles/zh/slots
+!profiles/zh/slot_programs
+
+!profiles/hi/profile.json
+!profiles/hi/custom_words.txt
+!profiles/hi/espeak_phonemes.txt
+!profiles/hi/phoneme_examples.txt
+!profiles/hi/frequent_words.txt
+!profiles/hi/sentences.ini
+!profiles/hi/stop_words.txt
+!profiles/hi/slots
+!profiles/hi/slot_programs
+
+!profiles/el/profile.json
+!profiles/el/custom_words.txt
+!profiles/el/espeak_phonemes.txt
+!profiles/el/phoneme_examples.txt
+!profiles/el/frequent_words.txt
+!profiles/el/sentences.ini
+!profiles/el/stop_words.txt
+!profiles/el/slots
+!profiles/el/slot_programs
+
+!profiles/es/profile.json
+!profiles/es/custom_words.txt
+!profiles/es/espeak_phonemes.txt
+!profiles/es/phoneme_examples.txt
+!profiles/es/frequent_words.txt
+!profiles/es/sentences.ini
+!profiles/es/stop_words.txt
+!profiles/es/slots
+!profiles/es/slot_programs
+
+!profiles/it/profile.json
+!profiles/it/custom_words.txt
+!profiles/it/espeak_phonemes.txt
+!profiles/it/phoneme_examples.txt
+!profiles/it/frequent_words.txt
+!profiles/it/sentences.ini
+!profiles/it/stop_words.txt
+!profiles/it/slots
+!profiles/it/slot_programs
+
+!profiles/ru/profile.json
+!profiles/ru/custom_words.txt
+!profiles/ru/espeak_phonemes.txt
+!profiles/ru/phoneme_examples.txt
+!profiles/ru/frequent_words.txt
+!profiles/ru/sentences.ini
+!profiles/ru/stop_words.txt
+!profiles/ru/slots
+!profiles/ru/slot_programs
+
+!profiles/pt/profile.json
+!profiles/pt/custom_words.txt
+!profiles/pt/espeak_phonemes.txt
+!profiles/pt/phoneme_examples.txt
+!profiles/pt/frequent_words.txt
+!profiles/pt/sentences.ini
+!profiles/pt/stop_words.txt
+!profiles/pt/slots
+!profiles/pt/slot_programs
+
+!profiles/sv/profile.json
+!profiles/sv/custom_words.txt
+!profiles/sv/espeak_phonemes.txt
+!profiles/sv/phoneme_examples.txt
+!profiles/sv/frequent_words.txt
+!profiles/sv/sentences.ini
+!profiles/sv/stop_words.txt
+!profiles/sv/slots
+!profiles/sv/slot_programs
+
+!profiles/vi/profile.json
+!profiles/vi/custom_words.txt
+!profiles/vi/espeak_phonemes.txt
+!profiles/vi/phoneme_examples.txt
+!profiles/vi/frequent_words.txt
+!profiles/vi/sentences.ini
+!profiles/vi/stop_words.txt
+!profiles/vi/slots
+!profiles/vi/slot_programs
+
+!profiles/ca/profile.json
+!profiles/ca/custom_words.txt
+!profiles/ca/espeak_phonemes.txt
+!profiles/ca/phoneme_examples.txt
+!profiles/ca/frequent_words.txt
+!profiles/ca/sentences.ini
+!profiles/ca/stop_words.txt
+!profiles/ca/slots
+!profiles/ca/slot_programs
+
+!profiles/nl/profile.json
+!profiles/nl/custom_words.txt
+!profiles/nl/espeak_phonemes.txt
+!profiles/nl/phoneme_examples.txt
+!profiles/nl/frequent_words.txt
+!profiles/nl/sentences.ini
+!profiles/nl/stop_words.txt
+!profiles/nl/slots
+!profiles/nl/slot_programs
+!profiles/nl/kaldi/custom_words.txt
+!profiles/nl/kaldi/espeak_phonemes.txt
+!profiles/nl/kaldi/phoneme_examples.txt
+
+!profiles/de/profile.json
+!profiles/de/custom_words.txt
+!profiles/de/espeak_phonemes.txt
+!profiles/de/phoneme_examples.txt
+!profiles/de/frequent_words.txt
+!profiles/de/sentences.ini
+!profiles/de/stop_words.txt
+!profiles/de/slots
+!profiles/de/slot_programs
+!profiles/de/kaldi/custom_words.txt
+!profiles/de/kaldi/espeak_phonemes.txt
+!profiles/de/kaldi/phoneme_examples.txt
+
+!profiles/fr/profile.json
+!profiles/fr/custom_words.txt
+!profiles/fr/espeak_phonemes.txt
+!profiles/fr/phoneme_examples.txt
+!profiles/fr/frequent_words.txt
+!profiles/fr/sentences.ini
+!profiles/fr/stop_words.txt
+!profiles/fr/slots
+!profiles/fr/slot_programs
+!profiles/fr/kaldi/custom_words.txt
+!profiles/fr/kaldi/espeak_phonemes.txt
+!profiles/fr/kaldi/phoneme_examples.txt
+
+!profiles/en/profile.json
+!profiles/en/custom_words.txt
+!profiles/en/espeak_phonemes.txt
+!profiles/en/phoneme_examples.txt
+!profiles/en/frequent_words.txt
+!profiles/en/sentences.ini
+!profiles/en/stop_words.txt
+!profiles/en/slots
+!profiles/en/slot_programs
+!profiles/en/kaldi/custom_words.txt
+!profiles/en/kaldi/espeak_phonemes.txt
+!profiles/en/kaldi/phoneme_examples.txt
+
+!rhasspy/profile_schema.json
+!rhasspy/*.py
+!rhasspy/train/*.py
+!rhasspy/train/jsgf2fst/*.py
+!*.py
+!VERSION

Makefile

@@ -5,7 +5,9 @@ SHELL := bash
 # Docker
 # -----------------------------------------------------------------------------
 
-docker: web-dist docker-amd64 docker-armhf docker-aarch64 docker-push manifest
+docker: web-dist docker-amd64 docker-armhf docker-aarch64
+
+docker-deploy: docker-push manifest
 
 docker-amd64:
 	docker build . -f docker/templates/dockerfiles/Dockerfile.prebuilt.alsa.all \

bin/generate-slots.py

@@ -18,22 +18,18 @@ def main():
             profile = json.load(profile_file)
             locale_name = profile["locale"] + ".UTF-8"
             locale.setlocale(locale.LC_ALL, locale_name)
-
-            slots_dir = profile_dir / "slots" / "rhasspy"
-            slots_dir.mkdir(parents=True, exist_ok=True)
-
-            # Day names
-            with open(slots_dir / "days", "w") as days_file:
-                for day_num in range(7):
-                    print(calendar.day_name[day_num], file=days_file)
-
-            # Month names
-            with open(slots_dir / "months", "w") as month_file:
-                for month_num in range(1, 13):
-                    print(calendar.month_name[month_num], file=month_file)
-
             print(locale_name)
 
+        slots_dir = profile_dir / "slots" / "rhasspy"
+        slots_dir.mkdir(parents=True, exist_ok=True)
+
+        # Day names
+        (slots_dir / "days").write_text('\n'.join(calendar.day_name))
+
+        # Month names
+        (slots_dir / "months").write_text('\n'.join(filter(None, calendar.month_name)))
+            
+
 # -----------------------------------------------------------------------------
 
 if __name__ == "__main__":

build-from-source.sh

@@ -329,31 +329,40 @@ case "${CPU_ARCH}" in
 esac
 
 requirements_file="${temp_dir}/requirements.txt"
+temp_requirements_file="${temp_dir}/temp_requirements.txt"
 cp "${this_dir}/requirements.txt" "${requirements_file}"
 
 # Exclude requirements
 if [[ -n "${no_flair}" ]]; then
     echo "Excluding flair from virtual environment"
-    sed -i '/^flair/d' "${requirements_file}"
+    sed '/^flair/d' "${requirements_file}" > "${temp_requirements_file}" &&
+        mv "${temp_requirements_file}" "${requirements_file}"
+
 fi
 
 if [[ -n "${no_precise}" ]]; then
     echo "Excluding Mycroft Precise from virtual environment"
-    sed -i '/^precise-runner/d' "${requirements_file}"
+    sed '/^precise-runner/d' "${requirements_file}" > "${temp_requirements_file}" &&
+        mv "${temp_requirements_file}" "${requirements_file}"
+
 fi
 
 if [[ -n "${no_adapt}" ]]; then
     echo "Excluding Mycroft Adapt from virtual environment"
-    sed -i '/^adapt-parser/d' "${requirements_file}"
+    sed '/^adapt-parser/d' "${requirements_file}" > "${temp_requirements_file}" &&
+        mv "${temp_requirements_file}" "${requirements_file}"
+
 fi
 
 if [[ -n "${no_google}" ]]; then
     echo "Excluding Google Text to Speech from virtual environment"
-    sed -i '/^google-cloud-texttospeech/d' "${requirements_file}"
+    sed '/^google-cloud-texttospeech/d' "${requirements_file}" > "${temp_requirements_file}" &&
+        mv "${temp_requirements_file}" "${requirements_file}"
 fi
 
 # Install everything except openfst first
-sed -i '/^openfst/d' "${requirements_file}"
+sed '/^openfst/d' "${requirements_file}" > "${temp_requirements_file}" &&
+        mv "${temp_requirements_file}" "${requirements_file}"
 
 "${python}" -m pip install -r "${requirements_file}"
 

docker/templates/all_profiles/profiles.txt

@@ -1,132 +1 @@
-COPY profiles/zh/profile.json \
-     profiles/zh/custom_words.txt \
-     profiles/zh/espeak_phonemes.txt \
-     profiles/zh/phoneme_examples.txt \
-     profiles/zh/frequent_words.txt \
-     profiles/zh/sentences.ini \
-     profiles/zh/stop_words.txt ${RHASSPY_APP}/profiles/zh/
-
-COPY profiles/hi/ \
-     profiles/hi/profile.json \
-     profiles/hi/custom_words.txt \
-     profiles/hi/espeak_phonemes.txt \
-     profiles/hi/phoneme_examples.txt \
-     profiles/hi/frequent_words.txt \
-     profiles/hi/sentences.ini \
-     profiles/hi/stop_words.txt ${RHASSPY_APP}/profiles/hi/
-
-COPY profiles/el/profile.json \
-     profiles/el/custom_words.txt \
-     profiles/el/espeak_phonemes.txt \
-     profiles/el/phoneme_examples.txt \
-     profiles/el/frequent_words.txt \
-     profiles/el/sentences.ini \
-     profiles/el/stop_words.txt ${RHASSPY_APP}/profiles/el/
-
-COPY profiles/de/profile.json \
-     profiles/de/custom_words.txt \
-     profiles/de/espeak_phonemes.txt \
-     profiles/de/phoneme_examples.txt \
-     profiles/de/frequent_words.txt \
-     profiles/de/sentences.ini \
-     profiles/de/stop_words.txt ${RHASSPY_APP}/profiles/de/
-
-COPY profiles/de/kaldi/custom_words.txt \
-     profiles/de/kaldi/espeak_phonemes.txt \
-     profiles/de/kaldi/phoneme_examples.txt \
-     ${RHASSPY_APP}/profiles/de/kaldi/
-
-COPY profiles/it/profile.json \
-     profiles/it/custom_words.txt \
-     profiles/it/espeak_phonemes.txt \
-     profiles/it/phoneme_examples.txt \
-     profiles/it/frequent_words.txt \
-     profiles/it/sentences.ini \
-     profiles/it/stop_words.txt ${RHASSPY_APP}/profiles/it/
-
-COPY profiles/es/profile.json \
-     profiles/es/custom_words.txt \
-     profiles/es/espeak_phonemes.txt \
-     profiles/es/phoneme_examples.txt \
-     profiles/es/frequent_words.txt \
-     profiles/es/sentences.ini \
-     profiles/es/stop_words.txt ${RHASSPY_APP}/profiles/es/
-
-COPY profiles/fr/profile.json \
-     profiles/fr/custom_words.txt \
-     profiles/fr/espeak_phonemes.txt \
-     profiles/fr/phoneme_examples.txt \
-     profiles/fr/frequent_words.txt \
-     profiles/fr/sentences.ini \
-     profiles/fr/stop_words.txt ${RHASSPY_APP}/profiles/fr/
-     
-COPY profiles/fr/kaldi/custom_words.txt \
-     profiles/fr/kaldi/espeak_phonemes.txt \
-     profiles/fr/kaldi/phoneme_examples.txt \
-     ${RHASSPY_APP}/profiles/fr/kaldi/
-
-COPY profiles/ru/profile.json \
-     profiles/ru/custom_words.txt \
-     profiles/ru/espeak_phonemes.txt \
-     profiles/ru/phoneme_examples.txt \
-     profiles/ru/frequent_words.txt \
-     profiles/ru/sentences.ini \
-     profiles/ru/stop_words.txt ${RHASSPY_APP}/profiles/ru/
-
-COPY profiles/nl/profile.json \
-     profiles/nl/custom_words.txt \
-     profiles/nl/espeak_phonemes.txt \
-     profiles/nl/phoneme_examples.txt \
-     profiles/nl/frequent_words.txt \
-     profiles/nl/sentences.ini \
-     profiles/nl/stop_words.txt ${RHASSPY_APP}/profiles/nl/
-
-COPY profiles/nl/kaldi/custom_words.txt \
-     profiles/nl/kaldi/espeak_phonemes.txt \
-     profiles/nl/kaldi/phoneme_examples.txt \
-     ${RHASSPY_APP}/profiles/nl/kaldi/
-
-COPY profiles/vi/profile.json \
-     profiles/vi/custom_words.txt \
-     profiles/vi/espeak_phonemes.txt \
-     profiles/vi/phoneme_examples.txt \
-     profiles/vi/frequent_words.txt \
-     profiles/vi/sentences.ini \
-     profiles/vi/stop_words.txt ${RHASSPY_APP}/profiles/vi/
-
-COPY profiles/pt/profile.json \
-     profiles/pt/custom_words.txt \
-     profiles/pt/espeak_phonemes.txt \
-     profiles/pt/phoneme_examples.txt \
-     profiles/pt/frequent_words.txt \
-     profiles/pt/sentences.ini \
-     profiles/pt/stop_words.txt ${RHASSPY_APP}/profiles/pt/
-
-COPY profiles/sv/profile.json \
-     profiles/sv/custom_words.txt \
-     profiles/sv/espeak_phonemes.txt \
-     profiles/sv/phoneme_examples.txt \
-     profiles/sv/frequent_words.txt \
-     profiles/sv/sentences.ini \
-     profiles/sv/stop_words.txt ${RHASSPY_APP}/profiles/sv/
-
-COPY profiles/ca/profile.json \
-     profiles/ca/custom_words.txt \
-     profiles/ca/espeak_phonemes.txt \
-     profiles/ca/phoneme_examples.txt \
-     profiles/ca/frequent_words.txt \
-     profiles/ca/sentences.ini \
-     profiles/ca/stop_words.txt ${RHASSPY_APP}/profiles/ca/
-
-COPY profiles/en/profile.json \
-     profiles/en/custom_words.txt \
-     profiles/en/espeak_phonemes.txt \
-     profiles/en/phoneme_examples.txt \
-     profiles/en/frequent_words.txt \
-     profiles/en/sentences.ini \
-     profiles/en/stop_words.txt ${RHASSPY_APP}/profiles/en/
-
-COPY profiles/en/kaldi/custom_words.txt \
-     profiles/en/kaldi/espeak_phonemes.txt \
-     profiles/en/kaldi/phoneme_examples.txt \
-     ${RHASSPY_APP}/profiles/en/kaldi/
+COPY profiles/ ${RHASSPY_APP}/profiles/

docker/templates/dockerfiles/Dockerfile.prebuilt.alsa.all

@@ -72,138 +72,7 @@ RUN chmod +x /run.sh
 
 
 
-COPY profiles/zh/profile.json \
-     profiles/zh/custom_words.txt \
-     profiles/zh/espeak_phonemes.txt \
-     profiles/zh/phoneme_examples.txt \
-     profiles/zh/frequent_words.txt \
-     profiles/zh/sentences.ini \
-     profiles/zh/stop_words.txt ${RHASSPY_APP}/profiles/zh/
-
-COPY profiles/hi/ \
-     profiles/hi/profile.json \
-     profiles/hi/custom_words.txt \
-     profiles/hi/espeak_phonemes.txt \
-     profiles/hi/phoneme_examples.txt \
-     profiles/hi/frequent_words.txt \
-     profiles/hi/sentences.ini \
-     profiles/hi/stop_words.txt ${RHASSPY_APP}/profiles/hi/
-
-COPY profiles/el/profile.json \
-     profiles/el/custom_words.txt \
-     profiles/el/espeak_phonemes.txt \
-     profiles/el/phoneme_examples.txt \
-     profiles/el/frequent_words.txt \
-     profiles/el/sentences.ini \
-     profiles/el/stop_words.txt ${RHASSPY_APP}/profiles/el/
-
-COPY profiles/de/profile.json \
-     profiles/de/custom_words.txt \
-     profiles/de/espeak_phonemes.txt \
-     profiles/de/phoneme_examples.txt \
-     profiles/de/frequent_words.txt \
-     profiles/de/sentences.ini \
-     profiles/de/stop_words.txt ${RHASSPY_APP}/profiles/de/
-
-COPY profiles/de/kaldi/custom_words.txt \
-     profiles/de/kaldi/espeak_phonemes.txt \
-     profiles/de/kaldi/phoneme_examples.txt \
-     ${RHASSPY_APP}/profiles/de/kaldi/
-
-COPY profiles/it/profile.json \
-     profiles/it/custom_words.txt \
-     profiles/it/espeak_phonemes.txt \
-     profiles/it/phoneme_examples.txt \
-     profiles/it/frequent_words.txt \
-     profiles/it/sentences.ini \
-     profiles/it/stop_words.txt ${RHASSPY_APP}/profiles/it/
-
-COPY profiles/es/profile.json \
-     profiles/es/custom_words.txt \
-     profiles/es/espeak_phonemes.txt \
-     profiles/es/phoneme_examples.txt \
-     profiles/es/frequent_words.txt \
-     profiles/es/sentences.ini \
-     profiles/es/stop_words.txt ${RHASSPY_APP}/profiles/es/
-
-COPY profiles/fr/profile.json \
-     profiles/fr/custom_words.txt \
-     profiles/fr/espeak_phonemes.txt \
-     profiles/fr/phoneme_examples.txt \
-     profiles/fr/frequent_words.txt \
-     profiles/fr/sentences.ini \
-     profiles/fr/stop_words.txt ${RHASSPY_APP}/profiles/fr/
-     
-COPY profiles/fr/kaldi/custom_words.txt \
-     profiles/fr/kaldi/espeak_phonemes.txt \
-     profiles/fr/kaldi/phoneme_examples.txt \
-     ${RHASSPY_APP}/profiles/fr/kaldi/
-
-COPY profiles/ru/profile.json \
-     profiles/ru/custom_words.txt \
-     profiles/ru/espeak_phonemes.txt \
-     profiles/ru/phoneme_examples.txt \
-     profiles/ru/frequent_words.txt \
-     profiles/ru/sentences.ini \
-     profiles/ru/stop_words.txt ${RHASSPY_APP}/profiles/ru/
-
-COPY profiles/nl/profile.json \
-     profiles/nl/custom_words.txt \
-     profiles/nl/espeak_phonemes.txt \
-     profiles/nl/phoneme_examples.txt \
-     profiles/nl/frequent_words.txt \
-     profiles/nl/sentences.ini \
-     profiles/nl/stop_words.txt ${RHASSPY_APP}/profiles/nl/
-
-COPY profiles/nl/kaldi/custom_words.txt \
-     profiles/nl/kaldi/espeak_phonemes.txt \
-     profiles/nl/kaldi/phoneme_examples.txt \
-     ${RHASSPY_APP}/profiles/nl/kaldi/
-
-COPY profiles/vi/profile.json \
-     profiles/vi/custom_words.txt \
-     profiles/vi/espeak_phonemes.txt \
-     profiles/vi/phoneme_examples.txt \
-     profiles/vi/frequent_words.txt \
-     profiles/vi/sentences.ini \
-     profiles/vi/stop_words.txt ${RHASSPY_APP}/profiles/vi/
-
-COPY profiles/pt/profile.json \
-     profiles/pt/custom_words.txt \
-     profiles/pt/espeak_phonemes.txt \
-     profiles/pt/phoneme_examples.txt \
-     profiles/pt/frequent_words.txt \
-     profiles/pt/sentences.ini \
-     profiles/pt/stop_words.txt ${RHASSPY_APP}/profiles/pt/
-
-COPY profiles/sv/profile.json \
-     profiles/sv/custom_words.txt \
-     profiles/sv/espeak_phonemes.txt \
-     profiles/sv/phoneme_examples.txt \
-     profiles/sv/frequent_words.txt \
-     profiles/sv/sentences.ini \
-     profiles/sv/stop_words.txt ${RHASSPY_APP}/profiles/sv/
-
-COPY profiles/ca/profile.json \
-     profiles/ca/custom_words.txt \
-     profiles/ca/espeak_phonemes.txt \
-     profiles/ca/phoneme_examples.txt \
-     profiles/ca/frequent_words.txt \
-     profiles/ca/sentences.ini \
-     profiles/ca/stop_words.txt ${RHASSPY_APP}/profiles/ca/
-
-COPY profiles/en/profile.json \
-     profiles/en/custom_words.txt \
-     profiles/en/espeak_phonemes.txt \
-     profiles/en/phoneme_examples.txt \
-     profiles/en/frequent_words.txt \
-     profiles/en/sentences.ini \
-     profiles/en/stop_words.txt ${RHASSPY_APP}/profiles/en/
-
-COPY profiles/en/kaldi/custom_words.txt \
-     profiles/en/kaldi/espeak_phonemes.txt \
-     profiles/en/kaldi/phoneme_examples.txt \
-     ${RHASSPY_APP}/profiles/en/kaldi/
+COPY profiles/ ${RHASSPY_APP}/profiles/
 
 COPY profiles/defaults.json ${RHASSPY_APP}/profiles/
 COPY docker/rhasspy ${RHASSPY_APP}/bin/

docs/hardware.md

@@ -4,6 +4,9 @@ Rhasspy is designed to be run on different kinds of hardware, such as:
 
 * Raspberry Pi 2-3 B/B+ (`armhf`/`aarch64`)
 * Desktop/laptop/server (`amd64`)
+* Raspberry Pi Zero (`armv6l`)
+    * You must use a [virtual environment](installation.md#virtual-environment)
+    * The [Kaldi speech recognizer](speech-to-text.md#kaldi) is **not** supported
 
 The table below summarizes architecture compatibility with Rhasspy's components:
 
@@ -30,7 +33,7 @@ The table below summarizes architecture compatibility with Rhasspy's components:
 
 To run Rhasspy on a Raspberry Pi, you'll need at least a 4 GB SD card and a good power supply. I highly recommend the [CanaKit Starter Kit](https://www.amazon.com/CanaKit-Raspberry-Starter-Premium-Black/dp/B07BCC8PK7), which includes a 32 GB SD card, a 2.5 A power supply, and a case.
 
-Some components of Rhasspy will not work on the Raspberry Pi 3 B+ model (`aarch64`). As of the time of this writing, these are:
+Some components of Rhasspy will not work on the Raspberry Pi 3 B+ model with a 64-bit operating system (`aarch64`). As of the time of this writing, these are:
 
 * [snowboy](wake-word.md#snowboy) (wake word)
 * [Mycroft Precise](wake-word.md#mycroft-precise) (wake word)

docs/installation.md

@@ -54,7 +54,13 @@ To update your Rhasspy Docker image, just run:
 ```bash
 docker pull synesthesiam/rhasspy-server:latest
 ```
-on your Rhasspy server and restart the Docker container.
+on your Rhasspy server and restart the Docker container. This may require running something like:
+
+```bash
+docker rm <container-name>
+```
+
+before doing a `docker run...`
 
 ## Hass.io
 
@@ -108,7 +114,14 @@ To update your Rhasspy virtual environment to the latest version, run:
 git pull origin master
 ```
 
-in your `rhasspy` directory. You should also re-build the web interface:
+in your `rhasspy` directory, and then update your Python dependencies:
+
+```bash
+source .venv/bin/activate
+pip3 install -r requirements.txt
+```
+
+You should also re-build the web interface:
 
 1. Install [yarn](https://yarnpkg.com) on your system
 2. Run `yarn build` in the `rhasspy` directory

docs/training.md

@@ -262,6 +262,13 @@ You can pass **arguments** to your program using the syntax `$name,arg1,arg2,...
 
 Like regular slots lists, slot programs can also be put in sub-directories under `slot_programs`. A program in `slot_programs/foo/bar` should be referenced in `sentences.ini` as `$foo/bar`.
 
+#### Built-in Slots
+
+Rhasspy includes a few built-in slots for each language:
+
+* `$rhasspy/days` - day names of the week
+* `$rhasspy/months` - month names of the year
+
 ### Converters
 
 By default, all named entity values in a recognized intent's JSON are strings. If you need a different data type, such as an integer or float, or want to do some kind of complex *conversion*, use a converter:

profiles/ca/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

profiles/de/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

profiles/el/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

profiles/en/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

profiles/es/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

profiles/fr/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

profiles/hi/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

profiles/it/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

profiles/nl/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

profiles/pt/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

profiles/ru/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

profiles/sv/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

profiles/vi/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

profiles/zh/slot_programs/rhasspy/number

@@ -17,9 +17,7 @@ def main():
         step = int(rest_args[0])
 
     if upper < lower:
-        temp_lower = lower
-        lower = upper
-        upper = temp_lower
+        lower, upper = upper, lower
 
     for n in range(lower, upper + 1, step):
         print(n)

rhasspy/actor.py

@@ -116,9 +116,6 @@ class RhasspyActor:
 
     def stop(self, block=True):
         """Stop this actor and its children."""
-        for child_actor in self._actors:
-            child_actor.stop(block=block)
-
         self.send(self, ActorExitRequest())
         if block:
             self._thread.join()
@@ -127,6 +124,15 @@ class RhasspyActor:
         """Main loop for this actor."""
         while self._running:
             message_dict = self._queue.get()
+            message = message_dict.get("message")
+            if isinstance(message, ActorExitRequest):
+                for child in self._actors:
+                    self.send(child, ActorExitRequest())
+
+                self._running = False
+                self.transition("stopped")
+                self.send(self._parent, ChildActorExited(self))
+
             self.on_receive(message_dict)
 
     @property
@@ -296,7 +302,7 @@ class InboxActor(RhasspyActor):
         return self
 
     def __exit__(self, *args):
-        self.stop(block=False)
+        self.stop(block=True)
 
 
 class ActorSystem:

rhasspy/dialogue.py

@@ -7,8 +7,8 @@ from pathlib import Path
 from typing import Any, Dict, List, Optional, Type
 
 import pydash
-import pywrapfst as fst
 import requests
+import rhasspynlu
 
 from rhasspy.actor import (
     ActorExitRequest,
@@ -555,12 +555,14 @@ class DialogueManager(RhasspyActor):
 
             self.transition("training_intent")
 
-            intent_fst_path = self.profile.read_path(
-                self.profile.get("intent.fsticuffs.intent_fst", "intent.fst")
+            intent_graph_path = self.profile.read_path(
+                self.profile.get("intent.fsticuffs.intent_graph", "intent.json")
             )
 
-            intent_fst = fst.Fst.read(str(intent_fst_path))
-            self.send(self.intent_trainer, TrainIntent(intent_fst))
+            with open(intent_graph_path, "r") as graph_file:
+                json_graph = json.load(graph_file)
+                intent_graph = rhasspynlu.json_to_graph(json_graph)
+                self.send(self.intent_trainer, TrainIntent(intent_graph))
         except Exception as e:
             self.transition("ready")
             self.send(self.training_receiver, ProfileTrainingFailed(str(e)))

rhasspy/events.py

@@ -246,8 +246,8 @@ class IntentForwarded:
 class TrainIntent:
     """Request to train intent recognizer."""
 
-    def __init__(self, intent_fst, receiver: Optional[RhasspyActor] = None) -> None:
-        self.intent_fst = intent_fst
+    def __init__(self, intent_graph, receiver: Optional[RhasspyActor] = None) -> None:
+        self.intent_graph = intent_graph
         self.receiver = receiver
 
 

rhasspy/intent.py

@@ -1,13 +1,11 @@
 """Support for intent recognition."""
 import concurrent.futures
-import io
 import json
 import logging
 import os
 import re
 import shutil
 import subprocess
-from pathlib import Path
 from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Type
 from urllib.parse import urljoin
 
@@ -18,7 +16,7 @@ from rhasspynlu import json_to_graph, recognize
 
 from rhasspy.actor import RhasspyActor
 from rhasspy.events import IntentRecognized, RecognizeIntent, SpeakSentence
-from rhasspy.utils import empty_intent, hass_request_kwargs
+from rhasspy.utils import empty_intent, hass_request_kwargs, load_converters
 
 # -----------------------------------------------------------------------------
 
@@ -137,32 +135,6 @@ class RemoteRecognizer(RhasspyActor):
 # -----------------------------------------------------------------------------
 
 
-class CliConverter:
-    """Command-line converter for intent recognition"""
-
-    def __init__(self, name: str, command_path: Path):
-        self.name = name
-        self.command_path = command_path
-
-    def __call__(self, *args, converter_args=None):
-        """Runs external program to convert JSON values"""
-        converter_args = converter_args or []
-        proc = subprocess.Popen(
-            [str(self.command_path)] + converter_args,
-            stdin=subprocess.PIPE,
-            stdout=subprocess.PIPE,
-            universal_newlines=True,
-        )
-
-        with io.StringIO() as input_file:
-            for arg in args:
-                json.dump(arg, input_file)
-
-            stdout, _ = proc.communicate(input=input_file.getvalue())
-
-            return [json.loads(line) for line in stdout.splitlines() if line.strip()]
-
-
 class FsticuffsRecognizer(RhasspyActor):
     """Recognize intents using OpenFST."""
 
@@ -188,33 +160,7 @@ class FsticuffsRecognizer(RhasspyActor):
         self.fuzzy = self.profile.get("intent.fsticuffs.fuzzy", True)
 
         # Load user-defined converters
-        converters_dir = Path(
-            self.profile.read_path(
-                self.profile.get("intent.fsticuffs.converters_dir", "converters")
-            )
-        )
-        if converters_dir.is_dir():
-            self._logger.debug("Loading converters from %s", converters_dir)
-            for converter_path in converters_dir.glob("**/*"):
-                if not converter_path.is_file():
-                    continue
-
-                # Retain directory structure in name
-                converter_name = str(
-                    converter_path.relative_to(converters_dir).with_suffix("")
-                )
-
-                # Run converter as external program.
-                # Input arguments are encoded as JSON on individual lines.
-                # Output values should be encoded as JSON on individual lines.
-                converter = CliConverter(converter_name, converter_path)
-
-                # Key off name without file extension
-                self.converters[converter_name] = converter
-
-                self._logger.debug(
-                    "Loaded converter %s from %s", converter_name, converter_path
-                )
+        self.converters = load_converters(self.profile)
 
         self.transition("loaded")
 

rhasspy/intent_train.py

@@ -9,14 +9,12 @@ import tempfile
 import time
 from collections import Counter, defaultdict
 from io import StringIO
-from typing import Any, Dict, List, Set, Type
+from typing import Any, Callable, Dict, List, Set, Type
 from urllib.parse import urljoin
 
 from rhasspy.actor import RhasspyActor
-from rhasspy.events import (IntentTrainingComplete, IntentTrainingFailed,
-                            TrainIntent)
-from rhasspy.utils import (lcm, make_sentences_by_intent,
-                           sample_sentences_by_intent)
+from rhasspy.events import IntentTrainingComplete, IntentTrainingFailed, TrainIntent
+from rhasspy.utils import lcm, make_sentences_by_intent, load_converters
 
 # -----------------------------------------------------------------------------
 
@@ -112,23 +110,30 @@ class FsticuffsIntentTrainer(DummyIntentTrainer):
 class FuzzyWuzzyIntentTrainer(RhasspyActor):
     """Save examples to JSON for fuzzy string matching later."""
 
+    def __init__(self):
+        RhasspyActor.__init__(self)
+        self.converters: Dict[str, Callable[..., Any]] = {}
+
     def in_started(self, message: Any, sender: RhasspyActor) -> None:
         """Handle messages in started state."""
         if isinstance(message, TrainIntent):
             try:
-                self.train(message.intent_fst)
+                self.train(message.intent_graph)
                 self.send(message.receiver or sender, IntentTrainingComplete())
             except Exception as e:
                 self._logger.exception("train")
                 self.send(message.receiver or sender, IntentTrainingFailed(repr(e)))
 
-    def train(self, intent_fst) -> None:
+    def train(self, intent_graph) -> None:
         """Save examples to JSON file."""
         examples_path = self.profile.write_path(
             self.profile.get("intent.fuzzywuzzy.examples_json")
         )
 
-        sentences_by_intent: Dict[str, Any] = make_sentences_by_intent(intent_fst)
+        converters = load_converters(self.profile)
+        sentences_by_intent = make_sentences_by_intent(
+            intent_graph, extra_converters=converters
+        )
         with open(examples_path, "w") as examples_file:
             json.dump(sentences_by_intent, examples_file, indent=4)
 
@@ -144,6 +149,10 @@ class FuzzyWuzzyIntentTrainer(RhasspyActor):
 class RasaIntentTrainer(RhasspyActor):
     """Uses Rasa NLU HTTP API to train a recognizer."""
 
+    def __init__(self):
+        RhasspyActor.__init__(self)
+        self.converters: Dict[str, Callable[..., Any]] = {}
+
     def in_started(self, message: Any, sender: RhasspyActor) -> None:
         """Handle messages in started state."""
         if isinstance(message, TrainIntent):
@@ -256,7 +265,9 @@ class RasaIntentTrainer(RhasspyActor):
                 response.raise_for_status()
             except Exception:
                 # Rasa gives quite helpful error messages, so extract them from the response.
-                raise Exception(f'{response.reason}: {json.loads(response.content)["message"]}')
+                raise Exception(
+                    f'{response.reason}: {json.loads(response.content)["message"]}'
+                )
 
 
 # -----------------------------------------------------------------------------
@@ -268,6 +279,14 @@ class RasaIntentTrainer(RhasspyActor):
 class AdaptIntentTrainer(RhasspyActor):
     """Configure a Mycroft Adapt engine."""
 
+    def __init__(self):
+        RhasspyActor.__init__(self)
+        self.converters: Dict[str, Callable[..., Any]] = {}
+
+    def to_started(self, from_state: str) -> None:
+        # Load user-defined converters
+        self.converters = load_converters(self.profile)
+
     def in_started(self, message: Any, sender: RhasspyActor) -> None:
         """Handle messages in started state."""
         if isinstance(message, TrainIntent):
@@ -287,9 +306,7 @@ class AdaptIntentTrainer(RhasspyActor):
         stop_words_path = self.profile.read_path("stop_words.txt")
         if os.path.exists(stop_words_path):
             with open(stop_words_path, "r") as stop_words_file:
-                stop_words = {
-                    line.strip() for line in stop_words_file if line.strip()
-                }
+                stop_words = {line.strip() for line in stop_words_file if line.strip()}
 
         # { intent: [ { 'text': ..., 'entities': { ... } }, ... ] }
         sentences_by_intent: Dict[str, Any] = make_sentences_by_intent(intent_fst)
@@ -410,6 +427,11 @@ class FlairIntentTrainer(RhasspyActor):
     def __init__(self):
         RhasspyActor.__init__(self)
         self.embeddings = []
+        self.converters: Dict[str, Callable[..., Any]] = {}
+
+    def to_started(self, from_state: str) -> None:
+        # Load user-defined converters
+        self.converters = load_converters(self.profile)
 
     def in_started(self, message: Any, sender: RhasspyActor) -> None:
         """Handle messages in started state."""
@@ -671,6 +693,7 @@ class CommandIntentTrainer(RhasspyActor):
     def __init__(self):
         RhasspyActor.__init__(self)
         self.command: List[str] = []
+        self.converters: Dict[str, Callable[..., Any]] = {}
 
     def to_started(self, from_state: str) -> None:
         """Transition to started state."""
@@ -682,6 +705,9 @@ class CommandIntentTrainer(RhasspyActor):
             for a in self.profile.get("training.intent.command.arguments", [])
         ]
 
+        # Load user-defined converters
+        self.converters = load_converters(self.profile)
+
         self.command = [program] + arguments
 
     def in_started(self, message: Any, sender: RhasspyActor) -> None:

rhasspy/train/__init__.py

@@ -165,9 +165,7 @@ def train_profile(profile_dir: Path, profile: Profile) -> Tuple[int, List[str]]:
         # Check for arguments.
         # Slot name retains argument(s).
         if "," in slot_name:
-            parts = slot_name.split(",")
-            slot_name = parts[0]
-            slot_args = parts[1:]
+            slot_name, *slot_args = slot_name.split(",")
         else:
             slot_args = None
 
@@ -228,7 +226,7 @@ def train_profile(profile_dir: Path, profile: Profile) -> Tuple[int, List[str]]:
             upper_bound = int(match.group(2))
             step = 1
 
-            if len(match.groups()) > 2:
+            if len(match.groups()) > 3:
                 # Exclude ,
                 step = int(match.group(3)[1:])
 
@@ -270,7 +268,7 @@ def train_profile(profile_dir: Path, profile: Profile) -> Tuple[int, List[str]]:
                 word.converters = ["int"]
                 return word
 
-            # Hard case, split into mutliple Words
+            # Hard case, split into multiple Words
             return jsgf.Sequence(
                 text=number_text,
                 type=jsgf.SequenceType.GROUP,

rhasspy/train/vocab_dict.py

@@ -91,7 +91,7 @@ def make_dict(
                 if (i < 1) or no_number:
                     print(word, pronounce, file=dictionary_file)
                 else:
-                    print(f"{word, i + 1}({pronounce})", file=dictionary_file)
+                    print(f"{word}({i + 1})", pronounce, file=dictionary_file)
 
             words_in_dict.add(word)
 

rhasspy/utils.py

@@ -1,23 +1,24 @@
 """Rhasspy utility functions."""
 import collections
-import concurrent.futures
 import gzip
 import io
 import itertools
+import json
 import logging
 import math
 import os
+import random
 import re
 import subprocess
 import threading
 import wave
 from collections import defaultdict
 from pathlib import Path
-from typing import (Any, Callable, Dict, Iterable, List, Mapping, Optional,
-                    Set, Tuple)
+from typing import Any, Callable, Dict, Iterable, List, Mapping, Optional, Set, Tuple
 
-import pywrapfst as fst
+import networkx as nx
 import rhasspynlu
+
 from num2words import num2words
 
 WHITESPACE_PATTERN = re.compile(r"\s+")
@@ -329,55 +330,45 @@ def grouper(iterable, n, fillvalue=None):
 # -----------------------------------------------------------------------------
 
 
-def make_sentences_by_intent(intent_fst: fst.Fst) -> Dict[str, Any]:
-    """Get all sentences from an FST."""
-    from rhasspy.train.jsgf2fst import fstprintall, symbols2intent
+def make_sentences_by_intent(
+    intent_graph: nx.DiGraph, num_samples: Optional[int] = None, extra_converters=None
+) -> Dict[str, List[Dict[str, Any]]]:
+    """Get all sentences from a graph."""
 
     # { intent: [ { 'text': ..., 'entities': { ... } }, ... ] }
     sentences_by_intent: Dict[str, Any] = defaultdict(list)
 
-    for symbols in fstprintall(intent_fst, exclude_meta=False):
-        intent = symbols2intent(symbols)
-        intent_name = intent["intent"]["name"]
-        sentences_by_intent[intent_name].append(intent)
+    start_node = None
+    end_node = None
+    for node, node_data in intent_graph.nodes(data=True):
+        if node_data.get("start", False):
+            start_node = node
+        elif node_data.get("final", False):
+            end_node = node
 
-    return sentences_by_intent
+        if start_node and end_node:
+            break
 
+    assert (start_node is not None) and (
+        end_node is not None
+    ), "Missing start/end node(s)"
 
-# -----------------------------------------------------------------------------
-
-
-def sample_sentences_by_intent(
-    intent_fst_paths: Dict[str, str], num_samples: int
-) -> Dict[str, Any]:
-    """Generate random intents"""
-    from rhasspy.train.jsgf2fst import fstprintall, symbols2intent
-
-    def sample_sentences(intent_name: str, intent_fst_path: str):
-        rand_fst = fst.Fst.read_from_string(
-            subprocess.check_output(
-                ["fstrandgen", f"--npath={num_samples}", intent_fst_path]
-            )
+    if num_samples is not None:
+        # Randomly sample
+        paths = random.sample(
+            list(nx.all_simple_paths(intent_graph, start_node, end_node)), num_samples
         )
+    else:
+        # Use generator
+        paths = nx.all_simple_paths(intent_graph, start_node, end_node)
 
-        sentences: List[Dict[str, Any]] = []
-        for symbols in fstprintall(rand_fst, exclude_meta=False):
-            intent = symbols2intent(symbols)
-            sentences.append(intent)
-
-        return sentences
-
-    # Generate samples in parallel
-    future_to_intent = {}
-    with concurrent.futures.ThreadPoolExecutor() as executor:
-        for intent_name, intent_fst_path in intent_fst_paths.items():
-            future = executor.submit(sample_sentences, intent_name, intent_fst_path)
-            future_to_intent[future] = intent_name
-
-    # { intent: [ { 'text': ..., 'entities': { ... } }, ... ] }
-    sentences_by_intent: Dict[str, Any] = {}
-    for future, intent_name in future_to_intent.items():
-        sentences_by_intent[intent_name] = future.result()
+    # TODO: Add converters
+    for path in paths:
+        _, recognition = rhasspynlu.fsticuffs.path_to_recognition(
+            path, intent_graph, extra_converters=extra_converters
+        )
+        assert recognition, "Path failed"
+        sentences_by_intent[recognition.intent.name].append(recognition.asdict())
 
     return sentences_by_intent
 
@@ -507,3 +498,64 @@ def get_all_intents(ini_paths: List[Path]) -> Dict[str, Any]:
         _LOGGER.exception("Failed to parse %s", ini_paths)
 
     return {}
+
+
+# -----------------------------------------------------------------------------
+
+
+class CliConverter:
+    """Command-line converter for intent recognition"""
+
+    def __init__(self, name: str, command_path: Path):
+        self.name = name
+        self.command_path = command_path
+
+    def __call__(self, *args, converter_args=None):
+        """Runs external program to convert JSON values"""
+        converter_args = converter_args or []
+        proc = subprocess.Popen(
+            [str(self.command_path)] + converter_args,
+            stdin=subprocess.PIPE,
+            stdout=subprocess.PIPE,
+            universal_newlines=True,
+        )
+
+        with io.StringIO() as input_file:
+            for arg in args:
+                json.dump(arg, input_file)
+
+            stdout, _ = proc.communicate(input=input_file.getvalue())
+
+            return [json.loads(line) for line in stdout.splitlines() if line.strip()]
+
+
+def load_converters(profile) -> Dict[str, Any]:
+    # Load user-defined converters
+    converters = {}
+
+    converters_dir = Path(
+        profile.read_path(profile.get("intent.fsticuffs.converters_dir", "converters"))
+    )
+
+    if converters_dir.is_dir():
+        _LOGGER.debug("Loading converters from %s", converters_dir)
+        for converter_path in converters_dir.glob("**/*"):
+            if not converter_path.is_file():
+                continue
+
+            # Retain directory structure in name
+            converter_name = str(
+                converter_path.relative_to(converters_dir).with_suffix("")
+            )
+
+            # Run converter as external program.
+            # Input arguments are encoded as JSON on individual lines.
+            # Output values should be encoded as JSON on individual lines.
+            converter = CliConverter(converter_name, converter_path)
+
+            # Key off name without file extension
+            converters[converter_name] = converter
+
+            _LOGGER.debug("Loaded converter %s from %s", converter_name, converter_path)
+
+    return converters