利用OpenAI和NVIDIA Riva，在Jetson上搭建一个AI聊天机器人

sudo nvpmodel -m 0 (Jetson Orin AGX, mode MAXN)sudo nvpmodel -m 0 (Jetson Xavier AGX, mode MAXN)sudo nvpmodel -m 2 (Jetson Xavier NX, mode MODE_15W_6CORE)

"default-：runtime": "nvidia"

wget --content-disposition https://ngc.nvidia.com/downloads/ngccli_arm64.zip && unzip ngccli_arm64.zip && chmod u+x ngc-cli/ngc

find ngc-cli/ -type f -exec md5sum {} + | LC_ALL=C sort | md5sum -c ngc-cli.md5

Add your current directory to path:echo "export PATH=\"\$PATH:$(pwd)/ngc-cli\"" >> ~/.bash_profile && source ~/.bash_profile

ln -s $(pwd)/ngc-cli/ngc [destination_path]/ngc

ngc config set

ngc registry resource download-version nvidia/riva/riva_quickstart_arm64:2.11.0

# Enable or Disable Riva Servicesservice_enabled_tts=trueservice_enabled_asr=trueservice_enabled_nmt=falseservice_enabled_nlp=false

cd riva_quickstart_arm64_v2.11.0

bash riva_init.shbash riva_start.sh

python3 transcribe_mic.py --list-devices

python3 transcribe_mic.py --input-device <device_number> --sample-rate-hz <sample_rate>

python3 talk.py --list-devices

.sh python3 talk.py --output-device <device_number> --sample-rate-hz <sample_rate>

pip3 install openai

import openai
openai.api_key = "openai-api-key"#using you openai key heremodel_engine = "gpt-3.5-turbo"ans = openai.ChatCompletion.create(    model=model_engine,    messages=[{"role": "user", "content": "you question"},          {"role": "assistant", "content": "The answer to the previous question "}]#use "assistant" to maintain context)
print(ans.choices[0].message)

with riva.client.audio_io.MicrophoneStream(                        args.sample_rate_hz,                        args.file_streaming_chunk,                        device=args.input_device,                ) as stream:                    for response in asr_service.streaming_response_generator(                            audio_chunks=stream,                            streaming_config=config,                    ):                        for result in response.results:                            if result.is_final:                                transcripts = result.alternatives[0].transcript  # print(output)                                output = transcripts

args1 = argparse.Namespace()args1.language_code = 'en-US'args1.sample_rate_hz = 48000 ##You can check the sample-rate of your own device to replace itargs1.stream = True #this shoule be trueargs1.output_device = 24 #You can check the port number of your own device to replace itservice = riva.client.SpeechSynthesisService(auth)#This code is request the Riva server to synthesize the languagenchannels = 1sampwidth = 2sound_stream = None

try:    if args1.output_device is not None:        #For playing audio during synthesis you will need to pass audio chunks to riv          a.client.audio_io.SoundCallBack as they arrive.        sound_stream = riva.client.audio_io.SoundCallBack(            args1.output_device, nchannels=nchannels, sampwidth=sampwidth,            framerate=args1.sample_rate_hz        )    if args1.stream:        #responses1 is the speech returned after synthesis,returning as an iterator        responses1 = service.synthesize_online(            answer, None, args1.language_code, sample_rate_hz=args1.sample_rate_hz        )        #Playing speech iteratively        for resp in responses1:            if sound_stream is not None:                sound_stream(resp.audio)finally:    if sound_stream is not None:        sound_stream.close()

if output == "hello ":#You can specify your wake-up word here,and remember to add a space after it    is_wakeup = True    anSwer('here', auth)    output = ""if output == "stop " and is_wakeup == True: #You can specify your pause word here,and remember to add a space after it    is_wakeup = False    anSwer('Bye! Have a great day!', auth)    output = ""

python3 <yourfilename.py> --input-device 24 --sample-rate-hz 48000