近实时智能应答 2D 数字人搭建

def transcribe_func_old(audio):
    audio_file = open(audio, "rb")
    file_name = audio_file.name
    print("audio_file: "+file_name)
    
    # Set up the job parameters
    job_name = "ai-bot-demo"
    text_output_bucket = 'ai-bot-text-material' #this bucket is in us-west-1
    text_output_key = 'transcriptions/question.json'
    text_output_key = 'transcriptions/'+job_name+'.json'
    language_code = 'zh-CN'

    # Upload the file to an S3 bucket
    audio_input_bucket_name = "ai-bot-audio-material"
    audio_input_s3_key = "questions/tmp-question-from-huggingface.wav"
    
    s3.upload_file(file_name, audio_input_bucket_name, audio_input_s3_key)
    
    # Construct the S3 bucket URI
    s3_uri = f"s3://{audio_input_bucket_name}/{audio_input_s3_key}"

    response = transcribe.list_transcription_jobs()
    
    # Iterate through the jobs and print their names
    for job in response['TranscriptionJobSummaries']:
        print(job['TranscriptionJobName'])
        if job['TranscriptionJobName'] == job_name:
            response = transcribe.delete_transcription_job(TranscriptionJobName=job_name)
            print("delete transcribe job response:"+str(response))

    # Create the transcription job
    response = transcribe.start_transcription_job(
        TranscriptionJobName=job_name,
        Media={'MediaFileUri': s3_uri},
        MediaFormat='wav',
        LanguageCode=language_code,
        OutputBucketName=text_output_bucket,
        OutputKey=text_output_key
    )
    
    print("start transcribe job response:"+str(response))
    job_name = response["TranscriptionJob"]["TranscriptionJobName"]
    
    # Wait for the transcription job to complete
    while True:
        status = transcribe.get_transcription_job(TranscriptionJobName=job_name)['TranscriptionJob']['TranscriptionJobStatus']
        if status in ['COMPLETED', 'FAILED']:
            break
        print("Transcription job still in progress...")
        time.sleep(1)
    
    # Get the transcript
    #transcript = transcribe.get_transcription_job(TranscriptionJobName=job_name)
    transcript_uri = transcribe.get_transcription_job(TranscriptionJobName=job_name)['TranscriptionJob']['Transcript']['TranscriptFileUri']
    print("transcript uri: " + str(transcript_uri))
    
    transcript_file_content = s3.get_object(Bucket=text_output_bucket, Key=text_output_key)['Body'].read().decode('utf-8')
    print(transcript_file_content)
    json_data = json.loads(transcript_file_content)

    # Extract the transcript value
    transcript_text = json_data['results']['transcripts'][0]['transcript']
    return transcript_text    

memory = ConversationBufferWindowMemory(k=5) 
conversation = ConversationChain(     
    llm=OpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], max_tokens=2048, temperature=0.5),      
     memory=memory, 
)

def polly_text_to_audio(audio_file_name, text, audio_format):

    if os.path.exists(audio_file_name):
        os.remove(audio_file_name)
        print("output mp3 file deleted successfully.")
    else:
        print("output mp3 file does not exist.")

    polly_response = polly.synthesize_speech(
        Text=text,
        OutputFormat=audio_format,  
        SampleRate='16000',
        VoiceId='Zhiyu',
        LanguageCode='cmn-CN',
        Engine='neural',
        LexiconNames=['xxxxCN']
    )   
    
    # Access the audio stream from the response
    if "AudioStream" in polly_response:
        # Note: Closing the stream is important because the service throttles on the
        # number of parallel connections. Here we are using contextlib.closing to
        # ensure the close method of the stream object will be called automatically
        # at the end of the with statement's scope.
            with closing(polly_response["AudioStream"]) as stream:
               try:
                # Open a file for writing the output as a binary stream
                    with open(audio_file_name, "wb") as file:
                       file.write(stream.read())
               except IOError as error:
                  # Could not write to file, exit gracefully
                  print(error)
                  sys.exit(-1)

    else:
        # The response didn't contain audio data, exit gracefully
        print("Could not stream audio")
        sys.exit(-1)

def generate_talk_with_audio(input, avatar_url, api_key = did_api_key):
    url = "https://api.d-id.com/talks"
    payload = {
        "script": {
            "type": "audio",
            "audio_url": input
        },
        "config": {
            "auto_match": "true",
            "result_format": "mp4"
        },
        "source_url": avatar_url
    }
    headers = {
        "accept": "application/json",
        "content-type": "application/json",
        "authorization": "Basic " + api_key
    }

    response = requests.post(url, json=payload, headers=headers)
    return response.json()


def get_a_talk(id, api_key = os.environ.get('DID_API_KEY')):
    url = "https://api.d-id.com/talks/" + id
    headers = {
        "accept": "application/json",
        "authorization": "Basic "+api_key
    }
    response = requests.get(url, headers=headers)
    return response.json()

def get_mp4_video(input, avatar_url=avatar_url):
    response = generate_talk_with_audio(input=input, avatar_url=avatar_url)
    print("DID response: "+str(response))
    talk = get_a_talk(response['id'])
    video_url = ""
    index = 0
    while index < 30:
        index += 1
        if 'result_url' in talk:    
            video_url = talk['result_url']
            return video_url
        else:
            time.sleep(1)
            talk = get_a_talk(response['id'])
    return video_url

response = generate_response(prompt)
# create variables to collect the stream of events
collected_events = []
completion_text = ''
sentance_to_polly = ''
separators = ['？','。','，','！']
already_polly_processed = ''
# iterate through the stream of events
for event in response:
    collected_events.append(event)  # save the event response
    event_text = event['choices'][0]['text']  # extract the text
    if event_text in separators:
        sentance_to_polly = completion_text.replace(already_polly_processed,'') 
        #print("sentance_to_polly: "+sentance_to_polly)
        polly_text_to_audio(response_audio_filename, sentance_to_polly, 'mp3')
        already_polly_processed = completion_text
    completion_text += event_text  # append the text
    print(event_text, end='', flush=True)  # print the delay and text

git lfs install
git clone https://huggingface.co/spaces/xdstone1/ai-bot-demo