Recherche avancée

Médias (11)

Mot : - Tags -/Elephant dreams

Sur d’autres sites (233)

  • Google Speech Recognition API output errors, unsure why they're occuring

    8 novembre 2019, par Requiem_7

    This is the output for when I feed flac files into Google’s Speech Recognition API. It says that if starts and finishes most of the files but then it gives me these errors when it nears the end. I have checked and all these files are native flac files. I took out a good chunk of the output above "source/out70.flac started" becuase it’s all the same besides the file number.

    source/out70.flac started
    
source/out25.flac started
    
source/out17.flac done
    
source/out18.flac started
    
source/out25.flac done
    
source/out20.flac done
    
source/out21.flac started
    
source/out10.flac done
    
source/out100.flac started
    
source/out14.flac done
    
source/out18.flac done
    
source/out21.flac done
    
Traceback (most recent call last):
    
  File "C:\Users\hmkur\AppData\Roaming\Python\Python37\site-packages\speech_recognition\__init__.py", line 203, in __enter__
    
    self.audio_reader = wave.open(self.filename_or_fileobject, "rb")
    
  File "C:\Program Files (x86)\Python37-32\lib\wave.py", line 510, in open
    
    return Wave_read(f)
    
  File "C:\Program Files (x86)\Python37-32\lib\wave.py", line 164, in __init__
    
    self.initfp(f)
    
  File "C:\Program Files (x86)\Python37-32\lib\wave.py", line 129, in initfp
    
    self._file = Chunk(file, bigendian = 0)
    
  File "C:\Program Files (x86)\Python37-32\lib\chunk.py", line 63, in __init__
    
    raise EOFError
    
EOFError
    

    
During handling of the above exception, another exception occurred:
    

    
Traceback (most recent call last):
    
  File "C:\Users\hmkur\AppData\Roaming\Python\Python37\site-packages\speech_recognition\__init__.py", line 208, in __enter__
    
    self.audio_reader = aifc.open(self.filename_or_fileobject, "rb")
    
  File "C:\Program Files (x86)\Python37-32\lib\aifc.py", line 917, in open
    
    return Aifc_read(f)
    
  File "C:\Program Files (x86)\Python37-32\lib\aifc.py", line 352, in __init__
    
    self.initfp(file_object)
    
  File "C:\Program Files (x86)\Python37-32\lib\aifc.py", line 314, in initfp
    
    chunk = Chunk(file)
    
  File "C:\Program Files (x86)\Python37-32\lib\chunk.py", line 63, in __init__
    
    raise EOFError
    
EOFError
    

    
During handling of the above exception, another exception occurred:
    

    
Traceback (most recent call last):
    
  File "C:\Users\hmkur\AppData\Roaming\Python\Python37\site-packages\speech_recognition\__init__.py", line 234, in __enter__
    
    self.audio_reader = aifc.open(aiff_file, "rb")
    
  File "C:\Program Files (x86)\Python37-32\lib\aifc.py", line 917, in open
    
    return Aifc_read(f)
    
  File "C:\Program Files (x86)\Python37-32\lib\aifc.py", line 358, in __init__
    
    self.initfp(f)
    
  File "C:\Program Files (x86)\Python37-32\lib\aifc.py", line 314, in initfp
    
    chunk = Chunk(file)
    
  File "C:\Program Files (x86)\Python37-32\lib\chunk.py", line 63, in __init__
    
    raise EOFError
    
EOFError
    

    
During handling of the above exception, another exception occurred:
    

    
Traceback (most recent call last):
    
  File "C:\Users\hmkur\Desktop\Python\Transcribing_Audio_GoogleAPI_Python\fast.py", line 92, in <module>
    
    all_text = pool.map(transcribe, enumerate(files))
    
  File "C:\Program Files (x86)\Python37-32\lib\multiprocessing\pool.py", line 268, in map
    
    return self._map_async(func, iterable, mapstar, chunksize).get()
    
  File "C:\Program Files (x86)\Python37-32\lib\multiprocessing\pool.py", line 657, in get
    
    raise self._value
    
  File "C:\Program Files (x86)\Python37-32\lib\multiprocessing\pool.py", line 121, in worker
    
    result = (True, func(*args, **kwds))
    
  File "C:\Program Files (x86)\Python37-32\lib\multiprocessing\pool.py", line 44, in mapstar
    
    return list(map(*args))
    
  File "C:\Users\hmkur\Desktop\Python\Transcribing_Audio_GoogleAPI_Python\fast.py", line 82, in transcribe
    
    with sr.AudioFile(name) as source:
    
  File "C:\Users\hmkur\AppData\Roaming\Python\Python37\site-packages\speech_recognition\__init__.py", line 236, in __enter__
    
    raise ValueError("Audio file could not be read as PCM WAV, AIFF/AIFF-C, or Native FLAC; check if file is corrupted or in another format")
    
ValueError: Audio file could not be read as PCM WAV, AIFF/AIFF-C, or Native FLAC; check if file is corrupted or in another format
    
</module>

  • mov : add more udta meta data recognition

    15 novembre 2012, par Xidorn Quan

    mov : add more udta meta data recognition

  • Free music recognition API

    12 mars 2014, par AmirH

    I'm developing an application to recognize the music played by speakers. It records 32 seconds of the sound played and send a request via an API of music recognition. So far I used Echonest. But my api_key has been banned because of to many requests since I published my freeware, used by more than 200 users.

    So I looked for MusicBrainz but it needs the exact duration of the entire song to receive a acceptable response, duration that my application can't guess.

    So I'm looking for a free music recognition API so my freeware works. Do you know one ?

    Note : I used Echonest by :

    I tried to use MusicBrainz by :

    • capturing 32 seconds with ffmpeg

    • generating the fingerprint using Chromaprint with this command :

      fpcalc sound.mp3 > fingerprint.txt

    • sending this command via cURL :

      curl -F "client=XXX" -F "meta=recordings" -F "duration=32" -F "fingerprint=ABC" "http://api.acoustid.org/v2/lookup" > info.txt

Navigation