issues
search
linto-ai
/
whisper-timestamped
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
GNU Affero General Public License v3.0
1.87k
stars
149
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
How to add new _ALIGNMENT_HEADS?
#139
JC1DA
closed
9 months ago
4
Please consider creating a node version
#138
55Cancri
closed
6 months ago
1
Language detection for large-v3
#136
andruxa-smirnov
closed
10 months ago
11
How to get the progress bar when transcribing through a Celery task ?
#135
dchapelet
closed
10 months ago
2
Large-v3
#134
takefy-dev
closed
10 months ago
11
German Audios translated instead of transcribed
#133
palibvb
closed
10 months ago
2
Issue with large-v3 model testing and channel mismatch error during audio processing
#132
Nondzu
closed
10 months ago
3
Unable to transcribe audio when using a fine-tuned whisper medium model
#130
yilmazay74
closed
10 months ago
2
Max length using python
#127
jeff11-1-1
closed
10 months ago
1
Key words in segment is missing
#126
mperetto
closed
11 months ago
4
whisper-timestamped is not thread-safe (AssertionError when multi-threading)
#124
Rtut654
opened
11 months ago
2
Timestamp always start at 0.
#122
Thomcle
closed
10 months ago
1
Question: dtw also possible for SeamlessMT4?
#121
doublex
closed
1 year ago
0
Sentences that definitely should be getting picked up are not
#118
Thomasssb1
closed
1 year ago
1
Option to change unit time (seconds -> milliseconds)
#116
Thomasssb1
opened
1 year ago
0
Entire sentences are not transcribed
#115
mirix
closed
10 months ago
2
NumbaDeprecationWarning
#114
xjq284
closed
10 months ago
1
Can I get phoneme from the word and score for its confidence ?
#113
tiennguyen12g
closed
10 months ago
1
add support for intel arc gpus
#112
furkanguzel161
closed
10 months ago
0
simple split audio file example using whisper-timestamped
#111
silvacarl2
closed
10 months ago
3
Why does it take so long to process a 1 minute video?
#110
Root-FTW
closed
10 months ago
3
Improve readability and grammar in README
#109
SimonBaars
closed
1 year ago
1
end time to early, cuts off the last word
#108
saltarob
opened
1 year ago
18
Punctuation and capitalisation
#106
mirix
closed
1 year ago
3
option `--suppress_token` to reduce hallucinations / output special noise descriptions
#105
misutoneko
closed
1 year ago
5
Feature Request: option to Allign the words with the vowel of the first syllable rather than the first consonant.
#103
JeromeNelsonC
opened
1 year ago
0
What are the best settings for most accurate/perfect time stamps?
#101
silvacarl2
closed
1 year ago
2
split audito into pieces directly from output of timestamps?
#100
silvacarl2
closed
1 year ago
2
ok, this is amazing but how can we transofrm it into an API?
#98
silvacarl2
closed
10 months ago
4
Timing off by multiple seconds
#97
tjthejuggler
closed
1 year ago
5
CUDA or is it me? Windows.
#96
pinballelectronica
closed
10 months ago
2
Update transcribe.py
#95
anita-arch
closed
10 months ago
3
generate duplicated phrases
#94
x180380
opened
1 year ago
8
Suggestion to change the way output-files are saved
#93
oep42
closed
1 year ago
3
Fixes typo in README.md
#92
NatanFreeman
closed
1 year ago
2
Trouble with timings
#91
boxabirds
closed
1 year ago
4
I want to get high performance - azure
#90
rairavi
closed
1 year ago
1
Deprecation warning
#89
aeschylus
closed
1 year ago
1
error for long (1 hr) hindi video - used large-v2 whisper model
#87
rairavi
closed
1 year ago
3
Words are correct but regular subtitles appear too early and linger?
#85
2600box
closed
1 year ago
3
Can't install on M2 Mac
#83
boxabirds
closed
1 year ago
3
[Idea] Basic timestamp validation
#82
misutoneko
opened
1 year ago
8
Improve Whisper transcription using transcript
#81
lenaten
closed
1 year ago
14
AssertionError with --vad, only with medium model
#80
misutoneko
closed
1 year ago
2
Try VAD with auditok
#78
Jeronymous
closed
9 months ago
1
High Memory Usage and "Killed: 9" Error.
#75
mcgreenwood
closed
1 year ago
5
VAD does not handle almost complete silence
#74
freddyertl
closed
9 months ago
23
--vad impacts recognition accuracy
#72
freddyertl
closed
1 year ago
6
End time of one word is the start time of the next one
#71
konradipipan
closed
1 year ago
1
Regular whisper model is still downloaded when using hugginface models
#70
blueskyleaf
closed
1 year ago
3
Previous
Next