diff --git a/demos/custom_streaming_asr/setup_docker.sh b/demos/custom_streaming_asr/setup_docker.sh old mode 100644 new mode 100755 diff --git a/demos/keyword_spotting/run.sh b/demos/keyword_spotting/run.sh old mode 100644 new mode 100755 diff --git a/demos/speaker_verification/run.sh b/demos/speaker_verification/run.sh old mode 100644 new mode 100755 diff --git a/demos/speech_recognition/run.sh b/demos/speech_recognition/run.sh old mode 100644 new mode 100755 index 19ce0ebb..e48ff3e9 --- a/demos/speech_recognition/run.sh +++ b/demos/speech_recognition/run.sh @@ -1,6 +1,7 @@ #!/bin/bash -wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav +wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav +wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav # asr paddlespeech asr --input ./zh.wav @@ -8,3 +9,18 @@ paddlespeech asr --input ./zh.wav # asr + punc paddlespeech asr --input ./zh.wav | paddlespeech text --task punc + + +# asr help +paddlespeech asr --help + + +# english asr +paddlespeech asr --lang en --model transformer_librispeech --input ./en.wav + +# model stats +paddlespeech stats --task asr + + +# paddlespeech help +paddlespeech --help diff --git a/demos/speech_server/asr_client.sh b/demos/speech_server/asr_client.sh old mode 100644 new mode 100755 diff --git a/demos/speech_server/cls_client.sh b/demos/speech_server/cls_client.sh old mode 100644 new mode 100755 diff --git a/demos/speech_server/server.sh b/demos/speech_server/server.sh old mode 100644 new mode 100755 index e5961286..fd719ffc --- a/demos/speech_server/server.sh +++ b/demos/speech_server/server.sh @@ -1,3 +1,3 @@ #!/bin/bash -paddlespeech_server start --config_file ./conf/application.yaml +paddlespeech_server start --config_file ./conf/application.yaml &> server.log & diff --git a/demos/speech_server/sid_client.sh b/demos/speech_server/sid_client.sh new file mode 100755 index 00000000..99bab21a --- /dev/null +++ b/demos/speech_server/sid_client.sh @@ -0,0 +1,10 @@ +#!/bin/bash + +wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav +wget -c https://paddlespeech.bj.bcebos.com/vector/audio/123456789.wav + +# sid extract +paddlespeech_client vector --server_ip 127.0.0.1 --port 8090 --task spk --input ./85236145389.wav + +# sid score +paddlespeech_client vector --server_ip 127.0.0.1 --port 8090 --task score --enroll ./85236145389.wav --test ./123456789.wav diff --git a/demos/speech_server/text_client.sh b/demos/speech_server/text_client.sh new file mode 100755 index 00000000..098f159f --- /dev/null +++ b/demos/speech_server/text_client.sh @@ -0,0 +1,4 @@ +#!/bin/bash + + +paddlespeech_client text --server_ip 127.0.0.1 --port 8090 --input 今天的天气真好啊你下午有空吗我想约你一起去吃饭 diff --git a/demos/speech_server/tts_client.sh b/demos/speech_server/tts_client.sh old mode 100644 new mode 100755 diff --git a/demos/streaming_asr_server/punc_server.py b/demos/streaming_asr_server/local/punc_server.py similarity index 100% rename from demos/streaming_asr_server/punc_server.py rename to demos/streaming_asr_server/local/punc_server.py diff --git a/demos/streaming_asr_server/streaming_asr_server.py b/demos/streaming_asr_server/local/streaming_asr_server.py similarity index 100% rename from demos/streaming_asr_server/streaming_asr_server.py rename to demos/streaming_asr_server/local/streaming_asr_server.py diff --git a/demos/streaming_asr_server/run.sh b/demos/streaming_asr_server/run.sh old mode 100644 new mode 100755 diff --git a/demos/streaming_asr_server/server.sh b/demos/streaming_asr_server/server.sh index f532546e..961cb046 100755 --- a/demos/streaming_asr_server/server.sh +++ b/demos/streaming_asr_server/server.sh @@ -1,9 +1,8 @@ -export CUDA_VISIBLE_DEVICE=0,1,2,3 - export CUDA_VISIBLE_DEVICE=0,1,2,3 +#export CUDA_VISIBLE_DEVICE=0,1,2,3 -# nohup python3 punc_server.py --config_file conf/punc_application.yaml > punc.log 2>&1 & +# nohup python3 local/punc_server.py --config_file conf/punc_application.yaml > punc.log 2>&1 & paddlespeech_server start --config_file conf/punc_application.yaml &> punc.log & -# nohup python3 streaming_asr_server.py --config_file conf/ws_conformer_wenetspeech_application.yaml > streaming_asr.log 2>&1 & +# nohup python3 local/streaming_asr_server.py --config_file conf/ws_conformer_wenetspeech_application.yaml > streaming_asr.log 2>&1 & paddlespeech_server start --config_file conf/ws_conformer_wenetspeech_application.yaml &> streaming_asr.log & diff --git a/demos/streaming_asr_server/test.sh b/demos/streaming_asr_server/test.sh index 67a5ec4c..386c7f89 100755 --- a/demos/streaming_asr_server/test.sh +++ b/demos/streaming_asr_server/test.sh @@ -7,5 +7,5 @@ paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8090 --input ./zh.wa # read the wav and call streaming and punc service # If `127.0.0.1` is not accessible, you need to use the actual service IP address. -paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8290 --punc.server_ip 127.0.0.1 --punc.port 8190 --input ./zh.wav +paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8090 --punc.server_ip 127.0.0.1 --punc.port 8190 --input ./zh.wav diff --git a/demos/streaming_tts_server/start_server.sh b/demos/streaming_tts_server/start_server.sh deleted file mode 100644 index 9c71f2fe..00000000 --- a/demos/streaming_tts_server/start_server.sh +++ /dev/null @@ -1,3 +0,0 @@ -#!/bin/bash -# start server -paddlespeech_server start --config_file ./conf/tts_online_application.yaml \ No newline at end of file diff --git a/demos/streaming_tts_server/test_client.sh b/demos/streaming_tts_server/test_client.sh deleted file mode 100644 index bd88f20b..00000000 --- a/demos/streaming_tts_server/test_client.sh +++ /dev/null @@ -1,9 +0,0 @@ -#!/bin/bash - -# http client test -# If `127.0.0.1` is not accessible, you need to use the actual service IP address. -paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol http --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav - -# websocket client test -# If `127.0.0.1` is not accessible, you need to use the actual service IP address. -# paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol websocket --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav diff --git a/demos/text_to_speech/run.sh b/demos/text_to_speech/run.sh index b1340241..2b588be5 100755 --- a/demos/text_to_speech/run.sh +++ b/demos/text_to_speech/run.sh @@ -4,4 +4,10 @@ paddlespeech tts --input 今天的天气不错啊 # Batch process -echo -e "1 欢迎光临。\n2 谢谢惠顾。" | paddlespeech tts \ No newline at end of file +echo -e "1 欢迎光临。\n2 谢谢惠顾。" | paddlespeech tts + +# Text Frontend +paddlespeech tts --input 今天是2022/10/29,最低温度是-3℃. + + + diff --git a/paddlespeech/server/bin/paddlespeech_client.py b/paddlespeech/server/bin/paddlespeech_client.py index e8e57fff..96368c0f 100644 --- a/paddlespeech/server/bin/paddlespeech_client.py +++ b/paddlespeech/server/bin/paddlespeech_client.py @@ -718,6 +718,7 @@ class VectorClientExecutor(BaseExecutor): logger.info(f"the input audio: {input}") handler = VectorHttpHandler(server_ip=server_ip, port=port) res = handler.run(input, audio_format, sample_rate) + logger.info(f"The spk embedding is: {res}") return res elif task == "score": from paddlespeech.server.utils.audio_handler import VectorScoreHttpHandler