mirror of
https://github.com/k2-fsa/sherpa-onnx.git
synced 2026-01-09 07:41:06 +08:00
e2b2d5ea57
# New Features - Added new example programs demonstrating streaming speech recognition from a microphone using Parakeet-TDT CTC and Zipformer Transducer models with voice activity detection. - These examples support microphone input via PortAudio and display recognized text incrementally. # Bug Fixes - Improved error handling and logic when opening microphone devices in several example programs for more reliable device initialization. # Chores - Updated build configuration to include new executable examples when PortAudio support is enabled.
130 lines
5.0 KiB
CMake
130 lines
5.0 KiB
CMake
include_directories(${PROJECT_SOURCE_DIR})
|
|
|
|
add_executable(streaming-zipformer-cxx-api ./streaming-zipformer-cxx-api.cc)
|
|
target_link_libraries(streaming-zipformer-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(streaming-zipformer-with-hr-cxx-api ./streaming-zipformer-with-hr-cxx-api.cc)
|
|
target_link_libraries(streaming-zipformer-with-hr-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(speech-enhancement-gtcrn-cxx-api ./speech-enhancement-gtcrn-cxx-api.cc)
|
|
target_link_libraries(speech-enhancement-gtcrn-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(kws-cxx-api ./kws-cxx-api.cc)
|
|
target_link_libraries(kws-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(streaming-zipformer-rtf-cxx-api ./streaming-zipformer-rtf-cxx-api.cc)
|
|
target_link_libraries(streaming-zipformer-rtf-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(whisper-cxx-api ./whisper-cxx-api.cc)
|
|
target_link_libraries(whisper-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(fire-red-asr-cxx-api ./fire-red-asr-cxx-api.cc)
|
|
target_link_libraries(fire-red-asr-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(moonshine-cxx-api ./moonshine-cxx-api.cc)
|
|
target_link_libraries(moonshine-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(sense-voice-cxx-api ./sense-voice-cxx-api.cc)
|
|
target_link_libraries(sense-voice-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(nemo-canary-cxx-api ./nemo-canary-cxx-api.cc)
|
|
target_link_libraries(nemo-canary-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
if(SHERPA_ONNX_ENABLE_PORTAUDIO)
|
|
add_executable(sense-voice-simulate-streaming-microphone-cxx-api
|
|
./sense-voice-simulate-streaming-microphone-cxx-api.cc
|
|
${CMAKE_CURRENT_LIST_DIR}/../sherpa-onnx/csrc/microphone.cc
|
|
)
|
|
target_link_libraries(sense-voice-simulate-streaming-microphone-cxx-api
|
|
sherpa-onnx-cxx-api
|
|
portaudio_static
|
|
)
|
|
|
|
add_executable(parakeet-tdt-simulate-streaming-microphone-cxx-api
|
|
./parakeet-tdt-simulate-streaming-microphone-cxx-api.cc
|
|
${CMAKE_CURRENT_LIST_DIR}/../sherpa-onnx/csrc/microphone.cc
|
|
)
|
|
target_link_libraries(parakeet-tdt-simulate-streaming-microphone-cxx-api
|
|
sherpa-onnx-cxx-api
|
|
portaudio_static
|
|
)
|
|
|
|
add_executable(parakeet-tdt-ctc-simulate-streaming-microphone-cxx-api
|
|
./parakeet-tdt-ctc-simulate-streaming-microphone-cxx-api.cc
|
|
${CMAKE_CURRENT_LIST_DIR}/../sherpa-onnx/csrc/microphone.cc
|
|
)
|
|
target_link_libraries(parakeet-tdt-ctc-simulate-streaming-microphone-cxx-api
|
|
sherpa-onnx-cxx-api
|
|
portaudio_static
|
|
)
|
|
|
|
add_executable(zipformer-ctc-simulate-streaming-microphone-cxx-api
|
|
./zipformer-ctc-simulate-streaming-microphone-cxx-api.cc
|
|
${CMAKE_CURRENT_LIST_DIR}/../sherpa-onnx/csrc/microphone.cc
|
|
)
|
|
target_link_libraries(zipformer-ctc-simulate-streaming-microphone-cxx-api
|
|
sherpa-onnx-cxx-api
|
|
portaudio_static
|
|
)
|
|
|
|
add_executable(zipformer-transducer-simulate-streaming-microphone-cxx-api
|
|
./zipformer-transducer-simulate-streaming-microphone-cxx-api.cc
|
|
${CMAKE_CURRENT_LIST_DIR}/../sherpa-onnx/csrc/microphone.cc
|
|
)
|
|
target_link_libraries(zipformer-transducer-simulate-streaming-microphone-cxx-api
|
|
sherpa-onnx-cxx-api
|
|
portaudio_static
|
|
)
|
|
endif()
|
|
|
|
if(SHERPA_ONNX_HAS_ALSA)
|
|
add_executable(sense-voice-simulate-streaming-alsa-cxx-api
|
|
./sense-voice-simulate-streaming-alsa-cxx-api.cc
|
|
${CMAKE_CURRENT_LIST_DIR}/../sherpa-onnx/csrc/alsa.cc
|
|
)
|
|
target_link_libraries(sense-voice-simulate-streaming-alsa-cxx-api
|
|
sherpa-onnx-cxx-api
|
|
portaudio_static
|
|
)
|
|
|
|
add_executable(zipformer-ctc-simulate-streaming-alsa-cxx-api
|
|
./zipformer-ctc-simulate-streaming-alsa-cxx-api.cc
|
|
${CMAKE_CURRENT_LIST_DIR}/../sherpa-onnx/csrc/alsa.cc
|
|
)
|
|
target_link_libraries(zipformer-ctc-simulate-streaming-alsa-cxx-api
|
|
sherpa-onnx-cxx-api
|
|
portaudio_static
|
|
)
|
|
|
|
if(DEFINED ENV{SHERPA_ONNX_ALSA_LIB_DIR})
|
|
target_link_libraries(sense-voice-simulate-streaming-alsa-cxx-api -L$ENV{SHERPA_ONNX_ALSA_LIB_DIR} -lasound)
|
|
target_link_libraries(zipformer-ctc-simulate-streaming-alsa-cxx-api -L$ENV{SHERPA_ONNX_ALSA_LIB_DIR} -lasound)
|
|
else()
|
|
target_link_libraries(sense-voice-simulate-streaming-alsa-cxx-api asound)
|
|
target_link_libraries(zipformer-ctc-simulate-streaming-alsa-cxx-api asound)
|
|
endif()
|
|
endif()
|
|
|
|
add_executable(sense-voice-with-hr-cxx-api ./sense-voice-with-hr-cxx-api.cc)
|
|
target_link_libraries(sense-voice-with-hr-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(dolphin-ctc-cxx-api ./dolphin-ctc-cxx-api.cc)
|
|
target_link_libraries(dolphin-ctc-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(vad-cxx-api ./vad-cxx-api.cc)
|
|
target_link_libraries(vad-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
if(SHERPA_ONNX_ENABLE_TTS)
|
|
add_executable(matcha-tts-zh-cxx-api ./matcha-tts-zh-cxx-api.cc)
|
|
target_link_libraries(matcha-tts-zh-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(matcha-tts-en-cxx-api ./matcha-tts-en-cxx-api.cc)
|
|
target_link_libraries(matcha-tts-en-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(kokoro-tts-en-cxx-api ./kokoro-tts-en-cxx-api.cc)
|
|
target_link_libraries(kokoro-tts-en-cxx-api sherpa-onnx-cxx-api)
|
|
|
|
add_executable(kokoro-tts-zh-en-cxx-api ./kokoro-tts-zh-en-cxx-api.cc)
|
|
target_link_libraries(kokoro-tts-zh-en-cxx-api sherpa-onnx-cxx-api)
|
|
endif()
|