我對語音識別主題很陌生我正在做一個項目，我可以在工作區(qū)中找到 Pepper bot 的一些用例。與 Pepper 一起玩，我們發(fā)現(xiàn)了它的語音識別能力的一些問題。我發(fā)現(xiàn)我們可以嘗試將它與外部引擎連接起來，我從 GCP 中選擇了 DialogFlow。也因為我發(fā)現(xiàn)了一些與該服務(wù)的集成。我使用了這個項目的代碼import tracebackfrom naoqi import qi# [START dialogflow_detect_intent_streaming]def detect_intent_stream(project_id, session_id, audio_file_path, language_code,ip): """Returns the result of detect intent with streaming audio as input. Using the same `session_id` between requests allows continuation of the conversation.""" import dialogflow_v2 as dialogflow session_client = dialogflow.SessionsClient() # Note: hard coding audio_encoding and sample_rate_hertz for simplicity. audio_encoding = dialogflow.enums.AudioEncoding.AUDIO_ENCODING_LINEAR_16 sample_rate_hertz = 44100 session_path = session_client.session_path(project_id, session_id) print('Session path: {}\n'.format(session_path)) def request_generator(audio_config, audio_file_path): query_input = dialogflow.types.QueryInput(audio_config=audio_config) # The first request contains the configuration. yield dialogflow.types.StreamingDetectIntentRequest( session=session_path, query_input=query_input) # Here we are reading small chunks of audio data from a local # audio file. In practice these chunks should come from # an audio input device. try: with open(audio_file_path, 'rb') as audio_file: while True: chunk = audio_file.read(4096) print(chunk) if not chunk: break except: traceback.print_exc() # The later requests contains audio data.
2 回答
拉風(fēng)的咖菲貓
TA貢獻1995條經(jīng)驗 獲得超2個贊
所以顯然你正在傳遞StringIO到detect_intent_stream：audio_file_path
with open(audio_file_path, 'rb') as audio_file:
您嘗試將其StringIO作為文件打開
但：
StringIO 實例已經(jīng)是一個打開的文件。另一方面，open 命令只接受文件名來返回一個打開的文件。StringIO 實例不適合作為文件名。關(guān)聯(lián)
所以request_generator函數(shù)detect_intent_stream需要看起來像：
def request_generator(audio_config, audio_file_path):
query_input = dialogflow.types.QueryInput(audio_config=audio_config)
yield dialogflow.types.StreamingDetectIntentRequest(
session=session_path, query_input=query_input)
while True:
chunk = audio_file_path.read(4096)
if not chunk:
break
yield dialogflow.types.StreamingDetectIntentRequest(
input_audio=chunk)
精慕HU
TA貢獻1845條經(jīng)驗 獲得超8個贊
您好，您的音頻文件或網(wǎng)絡(luò)連接可能有問題。您是否嘗試過發(fā)送一個簡單的文本或預(yù)先錄制的 wav 文件作為 dialogflow 的輸入？
這個腳本在我的辣椒上效果很好：（我的 wav 文件是 Mono，44100Hz，32Bit）
import os
import time
import sys
import uuid
import google
def printResponse(response):
print('=' * 20)
print('Query text: {}'.format(response.query_result.query_text.encode('utf-8')))
print('Detected intent: {} (confidence: {})'.format(
response.query_result.intent.display_name.encode('utf-8'),
response.query_result.intent_detection_confidence))
print('Fulfillment text: {}'.format(
response.query_result.fulfillment_text.encode('utf-8')))
def detect_intent_audio(project_id, session_id, audio_file_path,
language_code, sample_rate_hertz):
import dialogflow_v2 as dialogflow
session_client = dialogflow.SessionsClient()
# Note: hard coding audio_encoding and sample_rate_hertz for simplicity.
audio_encoding = dialogflow.enums.AudioEncoding.AUDIO_ENCODING_LINEAR_16
session = session_client.session_path(project_id, session_id)
with open(audio_file_path, 'rb') as audio_file:
input_audio = audio_file.read()
audio_config = dialogflow.types.InputAudioConfig(
audio_encoding=audio_encoding, language_code=language_code,
sample_rate_hertz=sample_rate_hertz)
query_input = dialogflow.types.QueryInput(audio_config=audio_config)
response = session_client.detect_intent(
session=session, query_input=query_input,
input_audio=input_audio)
printResponse(response)
def detect_intent_stream(project_id, session_id, audio_file_path,
language_code, sample_rate_hertz):
import dialogflow_v2 as dialogflow
session_client = dialogflow.SessionsClient()
# Note: hard coding audio_encoding and sample_rate_hertz for simplicity.
audio_encoding = dialogflow.enums.AudioEncoding.AUDIO_ENCODING_LINEAR_16
session_path = session_client.session_path(project_id, session_id)
def request_generator(audio_config, audio_file_path):
query_input = dialogflow.types.QueryInput(audio_config=audio_config)
# The first request contains the configuration.
yield dialogflow.types.StreamingDetectIntentRequest(
session=session_path, query_input=query_input)
# Here we are reading small chunks of audio data from a local
# audio file. In practice these chunks should come from
# an audio input device.
with open(audio_file_path, 'rb') as audio_file:
while True:
chunk = audio_file.read(4096)
if not chunk:
break
# The later requests contains audio data.
yield dialogflow.types.StreamingDetectIntentRequest(
input_audio=chunk)
audio_config = dialogflow.types.InputAudioConfig(
audio_encoding=audio_encoding, language_code=language_code,
sample_rate_hertz=sample_rate_hertz)
requests = request_generator(audio_config, audio_file_path)
responses = session_client.streaming_detect_intent(requests)
print('=' * 20)
for response in responses:
print('Intermediate transcript: "{}".'.format(
response.recognition_result.transcript.encode('utf-8')))
# Note: The result from the last response is the final transcript along
# with the detected content.
printResponse(response)
def detect_intent_texts(project_id, session_id, texts, language_code):
import dialogflow_v2 as dialogflow
session_client = dialogflow.SessionsClient()
session = session_client.session_path(project_id, session_id)
for text in texts:
text_input = dialogflow.types.TextInput(
text=text, language_code=language_code)
query_input = dialogflow.types.QueryInput(text=text_input)
response = session_client.detect_intent(
session=session, query_input=query_input)
printResponse(response)
project_id = 'my_project_id'
session_id = str(uuid.uuid4())
language_code = 'de'
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = os.path.join('/home/me/', 'xyz.json')
wav_path = os.path.join('/home/me/', 'audio.wav')
try:
print ("detect_intent_texts:")
detect_intent_texts(project_id, session_id, ["Hallo"], language_code)
print('=' * 20)
print ("detect_intent_audio:")
detect_intent_audio(project_id, session_id, wav_path, language_code, 44100)
print('=' * 20)
print ("detect_intent_stream:")
detect_intent_stream(project_id, session_id, wav_path, language_code, 44100)
print('=' * 20)
except google.api_core.exceptions.ServiceUnavailable:
print("503 Connect Failed")
添加回答
舉報
0/150
提交
取消