I try to run a chatbot script from inside a docker container, but it fails with the following error:
Traceback (most recent call last):
File "script.py", line 16, in <module>
with sr.Microphone() as source:
File "/home/datamastery/.local/lib/python3.8/site-packages/speech_recognition/__init__.py", line 86, in __init__
device_info = audio.get_device_info_by_index(device_index) if device_index is not None else audio.get_default_input_device_info()
File "/usr/local/lib/python3.8/dist-packages/pyaudio.py", line 949, in get_default_input_device_info
device_index = pa.get_default_input_device()
OSError: No Default Input Device Available
Dockerfile:
FROM python:3.6-stretch
RUN pip install --upgrade pip
RUN apt-get update && apt-get install -y espeak
RUN apt-get install portaudio19-dev -y
RUN useradd -rm -d /home/datamastery -s /bin/bash -g root -G sudo -u 1001 datamastery
USER datamastery
WORKDIR /home/datamastery
COPY script.py ./script.py
COPY requirements.txt ./requirements.txt
RUN pip install -r requirements.txt
CMD ["python", "script.py"]
requirements.txt
pyttsx3==2.90
transformers==4.6.1
SpeechRecognition==3.8.1
torch==1.8.1
PyAudio==0.2.11
script file:
# import library
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
import pyttsx3
import speech_recognition as sr
engineio = pyttsx3.init()
voices = engineio.getProperty("voices")
engineio.setProperty("rate", 130) # Aquí puedes seleccionar la velocidad de la voz
engineio.setProperty("voice", voices[0].id)
tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-medium")
model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-medium")
r = sr.Recognizer()
with sr.Microphone() as source:
for step in range(5):
r.adjust_for_ambient_noise(source)
print("Sprich...")
audio = r.listen(source, timeout=3)
print("Danke!")
audio_text = r.recognize_google(audio)
new_user_input_ids = tokenizer.encode(
audio_text + tokenizer.eos_token, return_tensors="pt"
)
bot_input_ids = (
torch.cat([chat_history_ids, new_user_input_ids], dim=-1)
if step > 0
else new_user_input_ids
)
chat_history_ids = model.generate(
bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id
)
print(chat_history_ids.shape)
print(type(chat_history_ids))
new_text = tokenizer.decode(
chat_history_ids[:, bot_input_ids.shape[-1] :][0], skip_special_tokens=True
)
print(new_text)
# recoginize_() method will throw a request error if the API is unreachable, hence using exception handling
try:
# using google speech recognition
engineio.say(new_text)
engineio.runAndWait()
except:
engineio.say("Sorry, did not understand you")
I tried the solution from this link: OSError: No Default Input Device Available, but it gives me a wrong index error (I added device_index=0).
File "/home/datamastery/.local/lib/python3.6/site-packages/speech_recognition/__init__.py", line 84, in __init__
assert 0 <= device_index < count, "Device index out of range ({} devices available; device index should be between 0 and {} inclusive)".format(count, count - 1)
AssertionError: Device index out of range (0 devices available; device index should be between 0 and -1 inclusive)
May the reason result from the fact, that ubuntu does not recognize my mic? If that is the case, do I have to install a library or set something in in my docker run command.
