more cli for speech demos

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

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 &

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

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

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  &
 

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
 

demos/streaming_tts_server/start_server.sh

@@ -1,3 +0,0 @@
-#!/bin/bash
-# start server
-paddlespeech_server start --config_file ./conf/tts_online_application.yaml

demos/streaming_tts_server/test_client.sh

@@ -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

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
+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℃.
+
+
+

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