diff --git a/examples/ffmpeg_vad_streaming/test.sh b/examples/ffmpeg_vad_streaming/test.sh new file mode 100755 index 00000000..13fefb7c --- /dev/null +++ b/examples/ffmpeg_vad_streaming/test.sh @@ -0,0 +1,30 @@ +#!/bin/bash + +set -xe + +THIS=$(dirname "$0") + +pushd ${THIS} + source ../tests.sh + + npm install $(get_npm_package_url) + npm install + + node ./index.js --audio $HOME/DeepSpeech/audio/2830-3980-0043.wav \ + --lm $HOME/DeepSpeech/models/lm.binary \ + --trie $HOME/DeepSpeech/models/trie \ + --model $HOME/DeepSpeech/models/output_graph.pbmm \ + --alphabet $HOME/DeepSpeech/models/alphabet.txt + + node ./index.js --audio $HOME/DeepSpeech/audio/4507-16021-0012.wav \ + --lm $HOME/DeepSpeech/models/lm.binary \ + --trie $HOME/DeepSpeech/models/trie \ + --model $HOME/DeepSpeech/models/output_graph.pbmm \ + --alphabet $HOME/DeepSpeech/models/alphabet.txt + + node ./index.js --audio $HOME/DeepSpeech/audio/8455-210777-0068.wav \ + --lm $HOME/DeepSpeech/models/lm.binary \ + --trie $HOME/DeepSpeech/models/trie \ + --model $HOME/DeepSpeech/models/output_graph.pbmm \ + --alphabet $HOME/DeepSpeech/models/alphabet.txt +popd diff --git a/examples/mic_vad_streaming/mic_vad_streaming.py b/examples/mic_vad_streaming/mic_vad_streaming.py index 6e7f4993..53a869e3 100755 --- a/examples/mic_vad_streaming/mic_vad_streaming.py +++ b/examples/mic_vad_streaming/mic_vad_streaming.py @@ -20,8 +20,10 @@ class Audio(object): CHANNELS = 1 BLOCKS_PER_SECOND = 50 - def __init__(self, callback=None, device=None, input_rate=RATE_PROCESS): + def __init__(self, callback=None, device=None, input_rate=RATE_PROCESS, file=None): def proxy_callback(in_data, frame_count, time_info, status): + if self.chunk is not None: + in_data = self.wf.readframes(self.chunk) callback(in_data) return (None, pyaudio.paContinue) if callback is None: callback = lambda in_data: self.buffer_queue.put(in_data) @@ -42,9 +44,13 @@ class Audio(object): 'stream_callback': proxy_callback, } + self.chunk = None # if not default device if self.device: kwargs['input_device_index'] = self.device + elif file is not None: + self.chunk = 320 + self.wf = wave.open(file, 'rb') self.stream = self.pa.open(**kwargs) self.stream.start_stream() @@ -96,8 +102,8 @@ class Audio(object): class VADAudio(Audio): """Filter & segment audio with voice activity detection.""" - def __init__(self, aggressiveness=3, device=None, input_rate=None): - super().__init__(device=device, input_rate=input_rate) + def __init__(self, aggressiveness=3, device=None, input_rate=None, file=None): + super().__init__(device=device, input_rate=input_rate, file=file) self.vad = webrtcvad.Vad(aggressiveness) def frame_generator(self): @@ -121,6 +127,9 @@ class VADAudio(Audio): triggered = False for frame in frames: + if len(frame) < 640: + return + is_speech = self.vad.is_speech(frame, self.sample_rate) if not triggered: @@ -162,7 +171,8 @@ def main(ARGS): # Start audio with VAD vad_audio = VADAudio(aggressiveness=ARGS.vad_aggressiveness, device=ARGS.device, - input_rate=ARGS.rate) + input_rate=ARGS.rate, + file=ARGS.file) print("Listening (ctrl-C to exit)...") frames = vad_audio.vad_collector() @@ -204,6 +214,8 @@ if __name__ == '__main__': help="Disable spinner") parser.add_argument('-w', '--savewav', help="Save .wav files of utterences to given directory") + parser.add_argument('-f', '--file', + help="Read from .wav file instead of microphone") parser.add_argument('-m', '--model', required=True, help="Path to the model (protocol buffer binary file, or entire directory containing all standard-named files for model)") @@ -214,7 +226,7 @@ if __name__ == '__main__': parser.add_argument('-t', '--trie', default='trie', help="Path to the language model trie file created with native_client/generate_trie. Default: trie") parser.add_argument('-d', '--device', type=int, default=None, - help="Device input index (Int) as listed by pyaudio.PyAudio.get_device_info_by_index(). If not provided, falls back to PyAudio.get_default_device()") + help="Device input index (Int) as listed by pyaudio.PyAudio.get_device_info_by_index(). If not provided, falls back to PyAudio.get_default_device().") parser.add_argument('-r', '--rate', type=int, default=DEFAULT_SAMPLE_RATE, help=f"Input device sample rate. Default: {DEFAULT_SAMPLE_RATE}. Your device may require 44100.") parser.add_argument('-nf', '--n_features', type=int, default=N_FEATURES, diff --git a/examples/mic_vad_streaming/test.sh b/examples/mic_vad_streaming/test.sh new file mode 100755 index 00000000..e35c7e5f --- /dev/null +++ b/examples/mic_vad_streaming/test.sh @@ -0,0 +1,21 @@ +#!/bin/bash + +set -xe + +THIS=$(dirname "$0") + +pushd ${THIS} + source ../tests.sh + + pip install --user $(get_python_wheel_url "$1") + pip install --user -r requirements.txt + + pulseaudio & + + python mic_vad_streaming.py \ + --model $HOME/DeepSpeech/models/output_graph.pbmm \ + --alphabet $HOME/DeepSpeech/models/alphabet.txt \ + --lm $HOME/DeepSpeech/models/lm.binary \ + --trie $HOME/DeepSpeech/models/trie \ + --file $HOME/DeepSpeech/audio/2830-3980-0043.wav +popd diff --git a/examples/nodejs_wav/test.sh b/examples/nodejs_wav/test.sh new file mode 100755 index 00000000..41ec4b78 --- /dev/null +++ b/examples/nodejs_wav/test.sh @@ -0,0 +1,18 @@ +#!/bin/bash + +set -xe + +THIS=$(dirname "$0") + +pushd ${THIS} + source ../tests.sh + + npm install $(get_npm_package_url) + npm install + + ln -s $HOME/DeepSpeech/models models + + node index.js $HOME/DeepSpeech/audio/2830-3980-0043.wav + node index.js $HOME/DeepSpeech/audio/8455-210777-0068.wav + node index.js $HOME/DeepSpeech/audio/4507-16021-0012.wav +popd diff --git a/examples/tests.sh b/examples/tests.sh new file mode 100755 index 00000000..78e63397 --- /dev/null +++ b/examples/tests.sh @@ -0,0 +1,23 @@ +#!/bin/bash + +set -xe + +THIS=$(dirname "$0") + +source ../../taskcluster/tc-tests-utils.sh + +DEP_TASK_ID=$(curl -s https://queue.taskcluster.net/v1/task/${TASK_ID} | python -c 'import json; import sys; print(" ".join(json.loads(sys.stdin.read())["dependencies"]));') + +get_python_wheel_url() +{ + local this_python_version=$1 + + extract_python_versions "${this_python_version}" "pyver" "pyver_pkg" "py_unicode_type" "pyconf" "pyalias" + + echo "$(get_python_pkg_url "${pyver_pkg}" "${py_unicode_type}" "deepspeech" https://queue.taskcluster.net/v1/task/${DEP_TASK_ID}/artifacts/public)" +} + +get_npm_package_url() +{ + echo "https://queue.taskcluster.net/v1/task/${DEP_TASK_ID}/artifacts/public/deepspeech-${DS_VERSION}.tgz" +} diff --git a/examples/vad_transcriber/audioTranscript_cmd.py b/examples/vad_transcriber/audioTranscript_cmd.py index b421d66c..552c58ad 100644 --- a/examples/vad_transcriber/audioTranscript_cmd.py +++ b/examples/vad_transcriber/audioTranscript_cmd.py @@ -22,9 +22,9 @@ def main(args): parser.add_argument('--stream', required=False, action='store_true', help='To use deepspeech streaming interface') args = parser.parse_args() - if args.stream is True and len(sys.argv[1:]) == 3: + if args.stream is True: print("Opening mic for streaming") - elif args.audio is not None and len(sys.argv[1:]) == 6: + elif args.audio is not None: logging.debug("Transcribing audio file @ %s" % args.audio) else: parser.print_help() diff --git a/examples/vad_transcriber/test.sh b/examples/vad_transcriber/test.sh new file mode 100755 index 00000000..5e4cf7dd --- /dev/null +++ b/examples/vad_transcriber/test.sh @@ -0,0 +1,23 @@ +#!/bin/bash + +set -xe + +THIS=$(dirname "$0") + +pushd ${THIS} + source ../tests.sh + + pip install --user $(get_python_wheel_url "$1") + pip install --user -r requirements.txt + + python audioTranscript_cmd.py \ + --audio $HOME/DeepSpeech/audio/2830-3980-0043.wav \ + --aggressive 0 \ + --model $HOME/DeepSpeech/models/ + + python audioTranscript_cmd.py \ + --audio $HOME/DeepSpeech/audio/2830-3980-0043.wav \ + --aggressive 0 \ + --model $HOME/DeepSpeech/models/ \ + --stream +popd diff --git a/taskcluster/examples-base.tyml b/taskcluster/examples-base.tyml new file mode 100644 index 00000000..855b92d9 --- /dev/null +++ b/taskcluster/examples-base.tyml @@ -0,0 +1,61 @@ +$if: '(event.event != "push") && (event.event != "tag")' +then: + taskId: ${taskcluster.taskId} + provisionerId: ${taskcluster.docker.provisionerId} + workerType: ${taskcluster.docker.workerType} + taskGroupId: ${taskcluster.taskGroupId} + schedulerId: ${taskcluster.schedulerId} + dependencies: + $map: { $eval: build.dependencies } + each(b): + $eval: as_slugid(b) + created: { $fromNow: '0 sec' } + deadline: { $fromNow: '1 day' } + expires: { $fromNow: '7 days' } + + extra: + github: + { $eval: taskcluster.github_events.pull_request } + + routes: + - "notify.irc-channel.${notifications.irc}.on-exception" + - "notify.irc-channel.${notifications.irc}.on-failed" + + scopes: [ + "queue:route:notify.irc-channel.*" + ] + + payload: + maxRunTime: { $eval: to_int(build.maxRunTime) } + image: ${build.docker_image} + + env: + DEEPSPEECH_MODEL: "https://github.com/lissyx/DeepSpeech/releases/download/tc-0.6.0/models.tar.gz" + DEEPSPEECH_AUDIO: "https://github.com/mozilla/DeepSpeech/releases/download/v0.4.1/audio-0.4.1.tar.gz" + PIP_DEFAULT_TIMEOUT: "60" + + command: + - "/bin/bash" + - "--login" + - "-cxe" + - $let: + extraSystemSetup: { $eval: strip(str(build.system_setup)) } + in: > + apt-get -qq update && apt-get -qq -y upgrade && apt-get -qq -y install git sox sudo && ${extraSystemSetup} && + adduser --system --home ${system.homedir.linux} ${system.username} && + cd ${system.homedir.linux} && + echo -e "#!/bin/bash\nset -xe\n env && id && mkdir ~/DeepSpeech/ && git clone --quiet ${event.head.repo.url} ~/DeepSpeech/ds/ && cd ~/DeepSpeech/ds && git checkout --quiet ${event.head.sha} && wget -O - $DEEPSPEECH_MODEL | tar -C ~/DeepSpeech/ -xzvf - && wget -O - $DEEPSPEECH_AUDIO | tar -C ~/DeepSpeech/ -xzvf - " > /tmp/clone.sh && chmod +x /tmp/clone.sh && + sudo -H -u ${system.username} /bin/bash /tmp/clone.sh && + sudo -H -u ${system.username} --preserve-env /bin/bash ${build.args.tests_cmdline} + + artifacts: + "public": + type: "directory" + path: "/tmp/artifacts/" + expires: { $fromNow: '7 days' } + + metadata: + name: ${build.metadata.name} + description: ${build.metadata.description} + owner: ${event.head.user.email} + source: ${event.head.repo.url} diff --git a/taskcluster/examples-ffmpeg_vad_streaming-node10.yml b/taskcluster/examples-ffmpeg_vad_streaming-node10.yml new file mode 100644 index 00000000..294cf46a --- /dev/null +++ b/taskcluster/examples-ffmpeg_vad_streaming-node10.yml @@ -0,0 +1,13 @@ +build: + template_file: examples-base.tyml + docker_image: "node:10" + dependencies: + - "node-package-cpu" + system_setup: + > + apt-get -qq -y install ffmpeg + args: + tests_cmdline: "${system.homedir.linux}/DeepSpeech/ds/examples/ffmpeg_vad_streaming/test.sh" + metadata: + name: "DeepSpeech examples: ffmpeg VAD Streaming NodeJS v10.x" + description: "DeepSpeech examples: ffmpeg VAD Streaming NodeJS v10.x" diff --git a/taskcluster/examples-ffmpeg_vad_streaming-node8.yml b/taskcluster/examples-ffmpeg_vad_streaming-node8.yml new file mode 100644 index 00000000..8decd1e6 --- /dev/null +++ b/taskcluster/examples-ffmpeg_vad_streaming-node8.yml @@ -0,0 +1,13 @@ +build: + template_file: examples-base.tyml + docker_image: "node:8" + dependencies: + - "node-package-cpu" + system_setup: + > + apt-get -qq -y install ffmpeg + args: + tests_cmdline: "${system.homedir.linux}/DeepSpeech/ds/examples/ffmpeg_vad_streaming/test.sh" + metadata: + name: "DeepSpeech examples: ffmpeg VAD Streaming NodeJS v8.x" + description: "DeepSpeech examples: ffmpeg VAD Streaming NodeJS v8.x" diff --git a/taskcluster/examples-mic_vad_streaming-py36.yml b/taskcluster/examples-mic_vad_streaming-py36.yml new file mode 100644 index 00000000..75635996 --- /dev/null +++ b/taskcluster/examples-mic_vad_streaming-py36.yml @@ -0,0 +1,13 @@ +build: + template_file: examples-base.tyml + docker_image: "python:3.6" + dependencies: + - "linux-amd64-cpu-opt" + system_setup: + > + apt-get -qq -y install portaudio19-dev pulseaudio + args: + tests_cmdline: "${system.homedir.linux}/DeepSpeech/ds/examples/mic_vad_streaming/test.sh 3.6.0:m" + metadata: + name: "DeepSpeech examples: mic VAD streaming Py3.6" + description: "DeepSpeech examples: mic VAD streaming Python 3.6" diff --git a/taskcluster/examples-mic_vad_streaming-py37.yml b/taskcluster/examples-mic_vad_streaming-py37.yml new file mode 100644 index 00000000..a333bf61 --- /dev/null +++ b/taskcluster/examples-mic_vad_streaming-py37.yml @@ -0,0 +1,13 @@ +build: + template_file: examples-base.tyml + docker_image: "python:3.7" + dependencies: + - "linux-amd64-cpu-opt" + system_setup: + > + apt-get -qq -y install portaudio19-dev pulseaudio + args: + tests_cmdline: "${system.homedir.linux}/DeepSpeech/ds/examples/mic_vad_streaming/test.sh 3.7.0:m" + metadata: + name: "DeepSpeech examples: mic VAD streaming Py3.7" + description: "DeepSpeech examples: mic VAD streaming Python 3.7" diff --git a/taskcluster/examples-nodejs_wav-node10.yml b/taskcluster/examples-nodejs_wav-node10.yml new file mode 100644 index 00000000..0efb90dd --- /dev/null +++ b/taskcluster/examples-nodejs_wav-node10.yml @@ -0,0 +1,10 @@ +build: + template_file: examples-base.tyml + docker_image: "node:10" + dependencies: + - "node-package-cpu" + args: + tests_cmdline: "${system.homedir.linux}/DeepSpeech/ds/examples/nodejs_wav/test.sh" + metadata: + name: "DeepSpeech examples: NodeJS WAV NodeJS v10.x" + description: "DeepSpeech examples: NodeJS WAV NodeJS v10.x" diff --git a/taskcluster/examples-nodejs_wav-node8.yml b/taskcluster/examples-nodejs_wav-node8.yml new file mode 100644 index 00000000..7cc359a6 --- /dev/null +++ b/taskcluster/examples-nodejs_wav-node8.yml @@ -0,0 +1,10 @@ +build: + template_file: examples-base.tyml + docker_image: "node:8" + dependencies: + - "node-package-cpu" + args: + tests_cmdline: "${system.homedir.linux}/DeepSpeech/ds/examples/nodejs_wav/test.sh" + metadata: + name: "DeepSpeech examples: NodeJS WAV NodeJS v8.x" + description: "DeepSpeech examples: NodeJS WAV NodeJS v8.x" diff --git a/taskcluster/examples-vad_transcriber-py35.yml b/taskcluster/examples-vad_transcriber-py35.yml new file mode 100644 index 00000000..17521d3c --- /dev/null +++ b/taskcluster/examples-vad_transcriber-py35.yml @@ -0,0 +1,10 @@ +build: + template_file: examples-base.tyml + docker_image: "python:3.5" + dependencies: + - "linux-amd64-cpu-opt" + args: + tests_cmdline: "${system.homedir.linux}/DeepSpeech/ds/examples/vad_transcriber/test.sh 3.5.0:m" + metadata: + name: "DeepSpeech examples: VAD transcriber Py3.5" + description: "DeepSpeech examples: VAD transcriberaming Python 3.5" diff --git a/taskcluster/examples-vad_transcriber-py36.yml b/taskcluster/examples-vad_transcriber-py36.yml new file mode 100644 index 00000000..287611e5 --- /dev/null +++ b/taskcluster/examples-vad_transcriber-py36.yml @@ -0,0 +1,10 @@ +build: + template_file: examples-base.tyml + docker_image: "python:3.6" + dependencies: + - "linux-amd64-cpu-opt" + args: + tests_cmdline: "${system.homedir.linux}/DeepSpeech/ds/examples/vad_transcriber/test.sh 3.6.0:m" + metadata: + name: "DeepSpeech examples: VAD transcriber Py3.6" + description: "DeepSpeech examples: VAD transcriberaming Python 3.6" diff --git a/taskcluster/examples-vad_transcriber-py37.yml b/taskcluster/examples-vad_transcriber-py37.yml new file mode 100644 index 00000000..931618c6 --- /dev/null +++ b/taskcluster/examples-vad_transcriber-py37.yml @@ -0,0 +1,10 @@ +build: + template_file: examples-base.tyml + docker_image: "python:3.7" + dependencies: + - "linux-amd64-cpu-opt" + args: + tests_cmdline: "${system.homedir.linux}/DeepSpeech/ds/examples/vad_transcriber/test.sh 3.7.0:m" + metadata: + name: "DeepSpeech examples: VAD transcriber Py3.7" + description: "DeepSpeech examples: VAD transcriberaming Python 3.7"