Speech audio file wav to Text - getting timed out

Question

I am trying to read a wav file of size 24.4MB, 9 mins 33  secs. using a simple python speech_recogniton code, i am getting below mentioned error. any suggestions would be great help.

Error: Could not request results from google Speech Recognition service; recognition connection failed: [Errno 32] Broken pipe

def readAudioFile(audio_file):
    r = sr.Recognizer()
    file = sr.AudioFile(audio_file)
    with file as source:

        audio = r.record(source)
        type(audio)
    try:
        message = r.recognize_google(audio)
        print(message)
        print("Data extracted from phone conversation:\n" + message)
    except sr.UnknownValueError:
        print("Google Speech Recognition could not understand audio")
    except sr.RequestError as e:
        print("Could not request results from google Speech Recognition service; {0}".format(e))

parser = argparse.ArgumentParser()
parser.add_argument("--file", "-f", type=str, required=True)
args = parser.parse_args()
audio_file = args.file
print(audio_file)
readAudioFile(audio_file)

Comments

I have a similar code and I get this error:

Could not request results from Google Speech Recognition service; recognition request failed: Bad Gateway

Answer 1

I think the error you are getting is because the file you are using crosses the API limit. Please check the limits of the API from the below mentioned link and see if the audio you are using is crossing the limit:

https://cloud.google.com/speech-to-text/quotas

Comments

Yes this is the problem, as i tried using it with smaller files and it worked fine.

---

thanks for the reply. ,as mentioned above, the code is working fine if the audio length is small. I am new to python, is there any example of how to do it with uri?

---

Hey @Shobha. To use uri, you have to first upload your file to Google Cloud Storage. You can refer the following link to know how to do this: https://www.youtube.com/watch?v=kdRuDaDyyBo

Then in you code, instead of the audio file path, use the uri pointing to your audio file in Google Cloud Storage. 

audio_file = gs://bucket-name/path_to_audio_file

---

Thank you so much for your reply :)

---

@Shobha Did it work for you?

---

You're Welcome :-) Shobha

Answer 2

@Omkar @Shobha

I tried doing it for a 2 minute audio file. It worked fine. I am not storing it in a text file i am simply printing the text.

The file is 3 MB.

https://www.edureka.co/community/31551/error-speech-to-text-codec-cannot-decode-the-bytes-position

Here you can have a look at the code.