Error: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED
#46 opened 12 months ago
by
duzm
Update README.md
1
#44 opened 12 months ago
by
Mucahit01
Training for translation
12
#43 opened 12 months ago
by
tirtohadi
Whisper-Large-V3 does not work with explicit use of dtype which is given in config.json
2
#42 opened 12 months ago
by
ait-paca
Update README.md
#41 opened 12 months ago
by
joey1895
What azure compute instance will work?
#40 opened 12 months ago
by
Jayantabasumatary1
Getting pipeline time estimate
1
#39 opened 12 months ago
by
wwilcz
how to evaluate use model-00001-of-00002.safetensors and model-00002-of-00002.safetensors
5
#36 opened 12 months ago
by
andyweiqiu
Does anyone know how to tag the speaker with Whisper?
4
#35 opened 12 months ago
by
Shaunnnnn
List of Supported Input Parameters?
1
#34 opened 12 months ago
by
souvik0306
Understands Finnish well
#33 opened 12 months ago
by
Ukuli
whisper outputs non stop no no no
3
#32 opened 12 months ago
by
rizwanishaq
Word timestamps and "return_language" at the same time
4
#31 opened 12 months ago
by
Oscaarjs
Batched files with different languages
#30 opened 12 months ago
by
Oscaarjs
Wrong Suffix after Downloading
1
#29 opened 12 months ago
by
seriphus
Add TF weights
1
#28 opened 12 months ago
by
vlad-skripniuk
Setting whisper-specific options in pipeline
1
#26 opened 12 months ago
by
MichalQU
no_speech_prob in pipeline?
3
#22 opened 12 months ago
by
rizwanishaq
language='cantonese' error
6
#21 opened 12 months ago
by
Boxp
Speculative Decoding Snippet Not Working
4
#20 opened 12 months ago
by
nateraw
Hallucination / repetition
2
#19 opened 12 months ago
by
persundstrom
can i use this free ?
7
#18 opened 12 months ago
by
AamirFarooq
How to get the language in default mode
1
#15 opened 12 months ago
by
nastasev
Error with word level timestamps
7
#12 opened 12 months ago
by
souvik0306
How to get Word and Verbose level transcription?
3
#11 opened 12 months ago
by
souvik0306
Translate using the API
2
#10 opened 12 months ago
by
SharatChandra
Error when running a model inference
5
#8 opened about 1 year ago
by
agonben23
TokenizerFast with tokenizer.json
2
#7 opened about 1 year ago
by
vubiqus
Why float16? Why not Float32
3
#4 opened about 1 year ago
by
ctranslate2-4you
Currently working on finetuning dataset for japanese anime speech
2
#3 opened about 1 year ago
by
joujiboi