diff options
| author |   Anuj Solanki <anuj603362@gmail.com> | 2024-06-16 18:49:45 +0530 |
|---|---|---|
| committer | Anuj Solanki <anuj603362@gmail.com> | 2024-09-07 20:16:14 +0530 |
| commit | 1144fcd343bc56f8c27ff73d3e76904010dbb832 (patch) | |
| tree | 490915cd969f19b4eb3b3dd480554b27c1058243 /agl_service_voiceagent/server.py | |
| parent | f2b62ba4da5a178221c3210c2d468cd684e626cc (diff) | |
Integrate Whisper AI into agl-service-voiceagent
V1:
- Integrated Whisper AI for speech-to-text functionality into
agl-service-voiceagent.
- Add support for both online and offline mode.
- Implemented a gRPC-based connection for online mode between
Whisper ASR service and voice-agent service.
V2:
- Update kuksa-interface
- Add whisper-cpp for speech-to-text functionality
- Add support to control media using mpd
- Fix audio recorder
Bug-AGL: SPEC-5200
Change-Id: I2661ae61ba2c3283bcfde26d6e4f498270240b19
Signed-off-by: Anuj Solanki <anuj603362@gmail.com>
Diffstat (limited to 'agl_service_voiceagent/server.py')
| -rw-r--r-- | agl_service_voiceagent/server.py | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/agl_service_voiceagent/server.py b/agl_service_voiceagent/server.py index aa107dc..b244aa4 100644 --- a/agl_service_voiceagent/server.py +++ b/agl_service_voiceagent/server.py @@ -14,6 +14,8 @@ # See the License for the specific language governing permissions and # limitations under the License. +import sys +sys.path.append("../") import grpc from concurrent import futures from agl_service_voiceagent.generated import voice_agent_pb2_grpc @@ -24,7 +26,8 @@ def run_server(): logger = get_logger() SERVER_URL = get_config_value('SERVER_ADDRESS') + ":" + str(get_config_value('SERVER_PORT')) print("Starting Voice Agent Service...") - print(f"STT Model Path: {get_config_value('STT_MODEL_PATH')}") + print(f"VOSK Model Path: {get_config_value('VOSK_MODEL_PATH')}") + print(f"WHISPER Model Path: {get_config_value('WHISPER_MODEL_PATH')}") print(f"Audio Store Directory: {get_config_value('BASE_AUDIO_DIR')}") server = grpc.server(futures.ThreadPoolExecutor(max_workers=10)) voice_agent_pb2_grpc.add_VoiceAgentServiceServicer_to_server(VoiceAgentServicer(), server) |