experiments/STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fix of issue #23

Browse Source
This commit is contained in:
Kelly Davis 2016-09-23 12:19:43 +02:00
parent ea38c68344
commit 26035f3626
5 changed files with 462 additions and 5327 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5779
DeepSpeech.ipynb
View File

File diff suppressed because it is too large Load Diff

BIN
images/Parallelism.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 91 KiB

2
util/audio/__init__.py
View File

@ -22,7 +22,7 @@ def audiofiles_to_audio_data_sets(audio_filenames, numcep, numcontext):
# - numcep dimensions for the current mfcc feature set
# - numcontext*numcep dimensions for each of the past and future (x2) mfcc feature set
# => so numcep + 2*numcontext*numcep
train_inputs = np.array([], np.float)
train_inputs = np.array([], np.float32)
train_inputs.resize((orig_inputs.shape[0], numcep + 2*numcep*numcontext))
# Prepare pre-fix post fix context (TODO: Fill empty_mfcc with MCFF of silence)

5
util/gpu/__init__.py Normal file
View File

@ -0,0 +1,5 @@
from tensorflow.python.client import device_lib
def get_available_gpus():
local_device_protos = device_lib.list_local_devices()
return [x.name for x in local_device_protos if x.device_type == 'GPU']

3
util/text/__init__.py
View File

@ -1,4 +1,5 @@
import numpy as np
import tensorflow as tf
# Constants
SPACE_TOKEN = '<space>'
@ -47,4 +48,4 @@ def sparse_tuple_from(sequences, dtype=np.int32):
values = np.asarray(values, dtype=dtype)
shape = np.asarray([len(sequences), np.asarray(indices).max(0)[1]+1], dtype=np.int64)
return indices, values, shape
return tf.SparseTensor(indices=indices, values=values, shape=shape)