 Jaikinator
|
280cfa3c35
|
fixed but where speaker dict included segment informations
|
2023-06-19 12:11:28 +02:00 |
|
|
Jaikinator
|
d3606a2dab
|
removed dependencie on ffmpeg python
will be dropped in future whisper realeases
|
2023-06-19 12:01:18 +02:00 |
|
|
Jaikinator
|
7bfd294bbd
|
fixed bug when only one speaker exists
|
2023-06-19 11:52:21 +02:00 |
|
|
Jaikinator
|
3ef7353db5
|
changed module imports
|
2023-06-16 15:10:08 +02:00 |
|
|
Jaikinator
|
1d25d61fa2
|
linting
|
2023-06-16 15:09:53 +02:00 |
|
|
Jaikinator
|
a653f0b05d
|
added new example usage
|
2023-06-16 15:09:44 +02:00 |
|
|
Jaikinator
|
61121aad92
|
updated version
|
2023-06-16 15:09:33 +02:00 |
|
|
Jaikinator
|
e4e5cfb4bc
|
linting
|
2023-06-16 15:06:18 +02:00 |
|
|
Jaikinator
|
c4c62c8ae1
|
added new file
|
2023-06-16 15:06:09 +02:00 |
|
|
Jaikinator
|
4f416f26f9
|
changed wrong file name
|
2023-06-16 15:03:25 +02:00 |
|
|
Jaikinator
|
cdfa872482
|
added segments to out dict
|
2023-06-16 15:00:39 +02:00 |
|
|
Jaikinator
|
52efd41d21
|
added Transcriptor class which handles
Transcription output
|
2023-06-16 15:00:22 +02:00 |
|
|
Jaikinator
|
b3c9bcc482
|
fixed wrong Transcript class params
|
2023-06-16 12:13:56 +02:00 |
|
|
Jaikinator
|
8a1bdda393
|
added verbose dafault value to be false
|
2023-06-16 12:11:13 +02:00 |
|
|
Jaikinator
|
713dd3bfd5
|
added cuda support
|
2023-06-16 12:10:11 +02:00 |
|
|
Jaikinator
|
de1ca22397
|
added dict as input type
|
2023-06-16 12:09:53 +02:00 |
|
|
Jaikinator
|
29e8a229dc
|
autotrancript works
|
2023-06-16 12:09:18 +02:00 |
|
|
Jaikinator
|
8ecc66cf29
|
linting
|
2023-06-16 11:30:47 +02:00 |
|
|
Jaikinator
|
edd6a0104c
|
removed pydub and use ffmpeg remove dependencies.
Droped pydub functionality and focuses on core components instead
|
2023-06-16 11:28:55 +02:00 |
|
|
Jaikinator
|
07acbc9464
|
added dummy class for output
|
2023-06-14 16:31:44 +02:00 |
|
|
Jaikinator
|
67e4e4585d
|
added kwargs parsing
|
2023-06-14 16:31:25 +02:00 |
|
|
Jaikinator
|
002c7b5189
|
auto transcript
|
2023-06-14 16:31:07 +02:00 |
|
|
Jaikinator
|
854469fb6e
|
audio processing
|
2023-06-14 16:30:57 +02:00 |
|
|
Jaikinator
|
34354c055f
|
changed imports
|
2023-06-14 16:30:29 +02:00 |
|
|
Jaikinator
|
90324e6ea7
|
added unittests
|
2023-06-14 16:30:15 +02:00 |
|
|
Jaikinator
|
2e6af75f81
|
del file
|
2023-06-14 16:30:05 +02:00 |
|
|
Jaikinator
|
7ee784457a
|
removed comments
|
2023-06-13 11:56:41 +02:00 |
|
|
Jaikinator
|
3cfdb894bf
|
updated get token
|
2023-06-13 09:54:14 +02:00 |
|
|
Jaikinator
|
157851f8fa
|
added compability with torchaudio
|
2023-06-13 08:25:58 +02:00 |
|
|
Jaikinator
|
a5693490df
|
removed renamed file
|
2023-06-13 07:05:57 +02:00 |
|
|
Jaikinator
|
edbe7ebb1d
|
added pytorch audio support
|
2023-06-12 16:38:19 +02:00 |
|
|
Jaikinator
|
6870d03f6b
|
better readbility
|
2023-06-12 15:56:52 +02:00 |
|
|
Jaikinator
|
b5dab23dd4
|
diarization in seconds
|
2023-06-12 15:54:28 +02:00 |
|
|
Jaikinator
|
ca42d631cd
|
added deprecated warning
|
2023-06-12 11:50:20 +02:00 |
|
|
Jaikinator
|
7aa2ed667f
|
changed file names
|
2023-06-12 11:49:17 +02:00 |
|
|
Jaikinator
|
6aae0f5b24
|
file name changed
|
2023-06-12 11:48:47 +02:00 |
|
|
Jaikinator
|
671c67415f
|
reworked diarization feature
|
2023-06-12 11:29:28 +02:00 |
|
|
Jaikinator
|
6710f05eaf
|
added unittest
|
2023-06-09 18:01:55 +02:00 |
|
|
Jaikinator
|
301a6e88b5
|
added sepearate functions to load models
|
2023-06-09 18:01:42 +02:00 |
|
|
Jaikinator
|
ee2cfc4319
|
reworked transcription class
|
2023-06-09 18:01:18 +02:00 |
|
|
Jaikinator
|
724c284474
|
added files to module init
|
2023-06-09 18:00:46 +02:00 |
|
|
Jaikinator
|
b019671f12
|
added files for rework
|
2023-06-09 18:00:29 +02:00 |
|
|
Jacob Schmieder
|
950f0834ef
|
Merge pull request #1 from JSchmie/update-dependencies
updated dependency files
|
2023-06-09 10:53:09 +02:00 |
|
|
Jaikinator
|
5ccede16ad
|
updated dependency files
|
2023-06-09 10:51:52 +02:00 |
|
|
Jaikinator
|
4031d58609
|
Fixed accidentally removed audio_file.export in covert audio
|
2023-04-05 21:17:08 +02:00 |
|
|
Jaikinator
|
73d2af2b21
|
fixed wrong bool using check_if_already_transcribed
|
2023-04-05 21:08:19 +02:00 |
|
|
Jaikinator
|
30859b0f4e
|
removed useless prints
added tqdm
added recognition for multiple Speakers
|
2023-04-05 20:04:29 +02:00 |
|
|
Jaikinator
|
e12a4f4967
|
bug fix
|
2023-01-10 21:16:22 +01:00 |
|
|
Jaikinator
|
3169b5c427
|
bug fix
|
2023-01-04 21:17:48 +01:00 |
|
|
Jaikinator
|
eb0cb6c23b
|
fixed bug with slower mp3
|
2022-12-29 16:03:08 +01:00 |
|