Spaces:
Running
Running
File size: 3,727 Bytes
e0a3506 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 |
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function
import argparse
import numpy as np
import shlex
import subprocess
import sys
import wave
import json
from deepspeech import Model, version
from timeit import default_timer as timer
try:
from shhlex import quote
except ImportError:
from pipes import quote
def convert_samplerate(audio_path, desired_sample_rate):
sox_cmd = 'sox {} --type raw --bits 16 --channels 1 --rate {} --encoding signed-integer --endian little --compression 0.0 --no-dither - '.format(
quote(audio_path), desired_sample_rate)
try:
output = subprocess.check_output(
shlex.split(sox_cmd), stderr=subprocess.PIPE)
except subprocess.CalledProcessError as e:
raise RuntimeError('SoX returned non-zero status: {}'.format(e.stderr))
except OSError as e:
raise OSError(e.errno, 'SoX not found, use {}hz files or install it: {}'.format(
desired_sample_rate, e.strerror))
return desired_sample_rate, np.frombuffer(output, np.int16)
def metadata_to_string(metadata):
return ''.join(token.text for token in metadata.tokens)
def words_from_candidate_transcript(metadata):
word = ""
word_list = []
word_start_time = 0
# Loop through each character
for i, token in enumerate(metadata.tokens):
# Append character to word if it's not a space
if token.text != " ":
if len(word) == 0:
# Log the start time of the new word
word_start_time = token.start_time
word = word + token.text
# Word boundary is either a space or the last character in the array
if token.text == " " or i == len(metadata.tokens) - 1:
word_duration = token.start_time - word_start_time
if word_duration < 0:
word_duration = 0
each_word = dict()
each_word["word"] = word
each_word["start_time "] = round(word_start_time, 4)
each_word["duration"] = round(word_duration, 4)
word_list.append(each_word)
# Reset
word = ""
word_start_time = 0
return word_list
def metadata_json_output(metadata):
json_result = dict()
json_result["transcripts"] = [{
"confidence": transcript.confidence,
"words": words_from_candidate_transcript(transcript),
} for transcript in metadata.transcripts]
return json.dumps(json_result, indent=2)
class VersionAction(argparse.Action):
def __init__(self, *args, **kwargs):
super(VersionAction, self).__init__(nargs=0, *args, **kwargs)
def __call__(self, *args, **kwargs):
print('DeepSpeech ', version())
exit(0)
def client(audio_file):
model_load_start = timer()
# sphinx-doc: python_ref_model_start
ds = Model("./uk.tflite")
# sphinx-doc: python_ref_model_stop
model_load_end = timer() - model_load_start
print('Loaded model in {:.3}s.'.format(model_load_end), file=sys.stderr)
desired_sample_rate = ds.sampleRate()
fin = wave.open(audio_file, 'rb')
fs_orig = fin.getframerate()
audio = np.frombuffer(fin.readframes(fin.getnframes()), np.int16)
audio_length = fin.getnframes() * (1/fs_orig)
fin.close()
print('Running inference.', file=sys.stderr)
inference_start = timer()
# sphinx-doc: python_ref_inference_start
result = ds.stt(audio)
print(result)
# sphinx-doc: python_ref_inference_stop
inference_end = timer() - inference_start
print('Inference took %0.3fs for %0.3fs audio file.' %
(inference_end, audio_length), file=sys.stderr)
return result
|