mirrors/DeepSpeech
2
0
Fork 0
mirror of https://github.com/mozilla/DeepSpeech.git synced 2025-10-26 11:19:39 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,241 Commits 63 Branches 109 Tags 17 GiB
dfdab7cb51
Commit Graph

1241 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
lissyx
dfdab7cb51
Merge pull request #1625 from lissyx/update-tf-master 
Update tf master
 2018-10-04 13:46:45 +02:00
Alexandre Lissy
593445d61a Merge remote-tracking branch 'upstream/master' into update-tf-master 2018-10-04 12:07:06 +02:00
lissyx
f4d064b2fe
Merge pull request #1623 from lissyx/remove-warpctc 
Remove WarpCTC
 2018-10-03 16:03:44 +02:00
Alexandre Lissy
d1d559355a Remove WarpCTC 2018-10-03 10:19:25 +02:00
lissyx
de54619ac5
Merge pull request #1527 from b-ak/master 
Transcribing longer audio clips
 2018-10-03 07:49:51 +02:00
bhargav-ak
89620bc448 Transcribing longer audio clips 
Prerequisites
-------------
~/Deepspeech$ sudo apt install virtualenv
~/Deepspeech$ cd examples/vad_transcriber
~/Deepspeech/examples/vad_transcriber$ virtualenv -p python3 venv
~/Deepspeech/examples/vad_transcriber$ source venv/bin/activate
(venv) ~/Deepspeech/examples/vad_transcriber$ pip3 install -r requirements.txt

Command line tool
-----------------
The command line tool processes a wav file of any duration and returns a trancript
which will the saved in the same directory as the input audio file.

(venv) ~/Deepspeech/examples/vad_transcriber
$ python3 audioTranscript_cmd.py --aggressive 1 --audio ./audio/guido-van-rossum.wav --model ./models/0.2.0/

Minimalistic GUI
----------------
The GUI tool does the same job as the CLI tool. The VAD is fixed at an aggressiveness of 1.
The output is displayed in the transcription window and saved into the directory as the input
audio file as well.

(venv) ~/Deepspeech/examples/vad_transcriber
$ python3 audioTranscript_gui.py

Changes(v1):
1. Using Deepspeech python module instead of subprocess
2. Moved VAD code to a module
3. Moved all files to bin/ and renamed README.md to Audio_Transcription.md

Changes(v2):
Renamed files

Changes (v2.1):
1. Refactoring between CMD and GUI code
2. Documenting pre-requisites with a virtualenv
3. Loading model only once per long wav file
4. CMD and GUI tool do the same job, perform VAD and consolidate the output.
5. Chunks are not saved in the disk. Using a numpy interger array to store them.

Changes (v2.2):
1. Argparse module for command line arguments
2. Everything in virtualenv, with a requirements.txt
3. Older APIs aligned with 0.2.0 release
4. Moved all files into examples/vad_transcriber

Changes (v2.3)
1. Updated requirements.txt
 2018-10-03 02:29:26 +05:30
lissyx
ca46382d50
Merge pull request #1620 from lissyx/update-tf-master 
Update tf master
 2018-10-02 22:03:39 +02:00
Alexandre Lissy
a8ce41ed62 Merge remote-tracking branch 'upstream/master' into update-tf-master 2018-10-02 20:52:18 +02:00
lissyx
240e0f222f
Merge pull request #1619 from lissyx/fix-tc-env 
Fix fallout from stricter YAML parser
 2018-10-02 20:06:21 +02:00
Alexandre Lissy
61a39c0a0a Fix fallout from stricter YAML parser 2018-10-02 19:16:53 +02:00
lissyx
2f9b551326
Merge pull request #1618 from lissyx/bump-v0.2.1-alpha.2 
Bump to v0.2.1-alpha.2
 2018-10-02 17:21:46 +02:00
Alexandre Lissy
97a46ba6e5 Bump to v0.2.1-alpha.2 2018-10-02 17:20:57 +02:00
lissyx
5465aa0176
Merge pull request #1617 from lissyx/update-trie-v2 
Update trie file to v2
 2018-10-02 17:16:45 +02:00
Alexandre Lissy
7d2c0e27f7 Update trie file to v2 2018-10-02 16:21:56 +02:00
lissyx
b9334122a6
Merge pull request #1615 from lissyx/one-shot-infer-fix-overlappingwindow 
Add single shot inference test coverage
 2018-10-02 15:20:07 +02:00
Alexandre Lissy
1b8b46ec95 Fix one shot inference 
Fixes #1612
 2018-10-02 14:20:45 +02:00
Alexandre Lissy
4daf1bf947 Add single shot inference test coverage 2018-10-02 14:20:45 +02:00
lissyx
c1e7244c6c
Merge pull request #1614 from lissyx/remove-base-maybedownload 
Remove deprecased tensorflow.contrib.learn.python.learn.datasets.base…
 2018-10-02 12:03:01 +02:00
Alexandre Lissy
94b8c5c1a3 Remove deprecased tensorflow.contrib.learn.python.learn.datasets.base.maybe_download 
Fixes #1531
Fixes #1477
 2018-10-02 10:59:16 +02:00
lissyx
8f62bec6fb
Merge pull request #1610 from lissyx/trie-opt 
Change TRIE format
 2018-10-02 08:01:46 +02:00
Alexandre Lissy
7c5e031b1f Change TRIE format 2018-10-01 19:03:36 +02:00
lissyx
72eaa2e8ce
Merge pull request #1604 from lissyx/r1.11-final 
Switch to stable TensorFlow r1.11
 2018-09-28 08:45:45 +02:00
Alexandre Lissy
6d0ef57946 Switch to stable TensorFlow r1.11 2018-09-28 07:25:49 +02:00
lissyx
63529387e3
Merge pull request #1603 from lissyx/fix-missing-copy 
Fix missing field in struct copy
 2018-09-28 06:09:47 +02:00
Alexandre Lissy
25ed3cb31e Fix missing field in struct copy 
Fixes #1602, #1563
 2018-09-28 05:10:15 +02:00
lissyx
6e67dcdbfc
Merge pull request #1600 from mozilla/issue1563 
Fixed a mismatched array new and delete
 2018-09-27 13:45:23 +02:00
kdavis-mozilla
5e1d7d004b Fixed mismatched array new and delete 2018-09-27 11:38:58 +02:00
lissyx
ae2cfe050a
Merge pull request #1596 from lissyx/bump-v0.2.1-alpha.1 
Bump to v0.2.1-alpha.1
 2018-09-26 18:47:20 +02:00
Alexandre Lissy
ff470eab5b Bump to v0.2.1-alpha.1 2018-09-26 18:46:44 +02:00
lissyx
15465765a9
Merge pull request #1595 from lissyx/fix-nodejs-python-prod 
Enforce same sox options as libsox for C++ client
 2018-09-26 18:31:16 +02:00
Alexandre Lissy
1362b50bfb Enforce same sox options as libsox for C++ client 
Fixes #1594
 2018-09-26 17:36:06 +02:00
lissyx
e17105fa2f
Merge pull request #1591 from lissyx/bump-v0.2.1-alpha.0 
Bump to v0.2.1-alpha.0
 2018-09-26 12:27:56 +02:00
Alexandre Lissy
7fd98fc9bd Bump to v0.2.1-alpha.0 2018-09-26 11:11:26 +02:00
lissyx
1385cf6f9b
Merge pull request #1582 from lissyx/update-dockerfile 
Adding TaskCluster testing of docker build
 2018-09-26 07:49:15 +02:00
Alexandre Lissy
1eb176bf50 Move to upstream TensorFlow for Docker 2018-09-25 20:25:03 +02:00
Alexandre Lissy
a0a9415ee9 Update Dockerfile to TensorFlow r1.11 2018-09-25 17:41:26 +02:00
Alexandre Lissy
6cf456fdb1 Adding TaskCluster testing of docker build 2018-09-25 17:39:07 +02:00
lissyx
8a5a0009c1
Merge pull request #1589 from lissyx/move-1.11 
Move remaining TensorFlow r1.6 to r1.11
 2018-09-25 17:38:44 +02:00
Alexandre Lissy
34564ad48c Move remaining TensorFlow r1.6 to r1.11 2018-09-25 17:09:25 +02:00
lissyx
f3dacc8ce9
Merge pull request #1577 from lissyx/tf-r1.11 
Tf r1.11
 2018-09-24 20:31:18 +02:00
Alexandre Lissy
1e0945e430 Update to TensorFlow r1.11 2018-09-24 19:23:44 +02:00
lissyx
07792b25c5
Merge pull request #1571 from lissyx/tf-master_20180920 
Update TensorFlow master artifacts
 2018-09-21 20:22:35 +02:00
Alexandre Lissy
897d945ccc Update TensorFlow version 2018-09-21 19:24:45 +02:00
Alexandre Lissy
ed039d0e59 Update TensorFlow master artifacts 2018-09-21 16:15:31 +02:00
lissyx
d0035d8583
Merge pull request #1567 from lissyx/tf-master_20180917 
Tf master 20180917
 2018-09-21 07:30:51 +02:00
Alexandre Lissy
8561b9f794 Upgrade TensorFlow 2018-09-20 22:54:08 +02:00
Alexandre Lissy
64ae266bfc Add missing ops 2018-09-20 21:03:36 +02:00
Alexandre Lissy
4ea2a84fc7 Change double_conversion namespace 2018-09-20 21:03:36 +02:00
Alexandre Lissy
5ad89c85ec Update expected TensorFlow 2018-09-20 21:03:36 +02:00
Alexandre Lissy
4c2b652347 Move to TensorFlow master 20180917 2018-09-20 21:03:36 +02:00