I want to convert some audio files to text in offline mode using SpeechRecognition module. I am able to convert it but it's 0% accurate. Can anyone suggest how to make it more accurate? Here's the code I am using:
def convert_wav_to_text(path):
"""
Splitting the large audio file into chunks
and apply speech recognition on each of these chunks
"""
# open the audio file using pydub
sound = AudioSegment.from_wav(path)
# split audio sound where silence is 700 miliseconds or more and get chunks
chunks = split_on_silence(sound,
# experiment with this value for your target audio file
min_silence_len = 500,
# adjust this per requirement
silence_thresh = sound.dBFS-14,
# keep the silence for 1 second, adjustable as well
keep_silence=500,
)
folder_name = "audio-chunks"
# create a directory to store the audio chunks
if not os.path.isdir(folder_name):
os.mkdir(folder_name)
whole_text = ""
# process each chunk
for i, audio_chunk in enumerate(chunks, start=1):
# export audio chunk and save it in
# the `folder_name` directory.
chunk_filename = os.path.join(folder_name, f"chunk{i}.wav")
audio_chunk.export(chunk_filename, format="wav")
# recognize the chunk
with sr.AudioFile(chunk_filename) as source:
audio_listened = r.record(source)
# try converting it to text
try:
text = r.recognize_sphinx(audio_listened)
except sr.UnknownValueError as e:
print("Error:", str(e))
else:
text = f"{text.capitalize()}. "
whole_text += text
# return the text for all chunks detected
num = path.split('.')[0]
file = open(num+'.txt', 'w')
file.write(whole_text)
file.close()
convert_wav_to_text("1.wav")
I am attaching the audio file also: 1.wav
