speech2text2.py

from __future__ import print_function
import os
from os import environ,path
from pocketsphinx import Pocketsphinx, get_model_path, get_data_path

model_path = get_model_path()
data_path = path.join(path.dirname(path.realpath(os.curdir))+'\\pyexperiments\\data')#get_data_path()

config = {
    'hmm': os.path.join(model_path, 'en-us'),
    'lm': os.path.join(model_path, 'en-us.lm.bin'),
    'dict': os.path.join(model_path, 'cmudict-en-us.dict')
}

ps = Pocketsphinx(**config)
ps.decode(
    audio_file=os.path.join(data_path, 'out.wav'),
    buffer_size=2048,
    no_search=False,
    full_utt=False
)

#print(ps.segments()) # => ['<s>', '<sil>', 'go', 'forward', 'ten', 'meters', '</s>']
#print('Detailed segments:', *ps.segments(detailed=True), sep='\n') # => [
#     word, prob, start_frame, end_frame
#     ('<s>', 0, 0, 24)
#     ('<sil>', -3778, 25, 45)
#     ('go', -27, 46, 63)
#     ('forward', -38, 64, 116)
#     ('ten', -14105, 117, 152)
#     ('meters', -2152, 153, 211)
#     ('</s>', 0, 212, 260)
# ]

print("hypothesis:\n" + ps.hypothesis())  # => go forward ten meters
print("probablity of correct:\n"+ str(ps.probability())) # => -32079
print("score:\n" + str(ps.score()))       # => -7066
print("confidence:\n" + str(ps.confidence()))  # => 0.04042641466841839

#print(*ps.best(count=10), sep='\n') # => [
#     ('go forward ten meters', -28034)
#     ('go for word ten meters', -28570)
#     ('go forward and majors', -28670)
#     ('go forward and meters', -28681)
#     ('go forward and readers', -28685)
#     ('go forward ten readers', -28688)
#     ('go forward ten leaders', -28695)
#     ('go forward can meters', -28695)
#     ('go forward and leaders', -28706)
#     ('go for work ten meters', -28722)
# ]