shashikg WhisperS2T issues

shashikg / WhisperS2T

An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine

MIT License

315 stars 32 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Compatibility with turbo-large-v3

#77 moumeneb98 opened 2 days ago
0
Invalid handle. Cannot load symbol cudnnCreateTensorDescriptor Error

#76 andriken opened 2 weeks ago
0
Are utterance-level timings available?

#75 abresch opened 1 month ago
0
Replace `multiprocessing.dummy.Pool()` with `concurrent.futures.ThreadPoolExecutor()` so whisper_s2t instance can run separately with `multiprocessing.Process()`

#74 kirillsaidov opened 1 month ago
0
Whisper HF does not work

#73 eschmidbauer opened 1 month ago
0
tokenizer.json file?

#72 tianchengcheng-cn closed 1 month ago
2
Add Lora Dynamic switching for inference

#71 Jeevi10 opened 3 months ago
4
Can't find decoder_config.json when using tensorrt-llm large-v3 model

#70 Nyralei closed 3 months ago
1
bad_word_list argument for TRT backend is ignored

#69 yv0vaa opened 3 months ago
0
data/KINCAID46/manifest_wav.tsv?

#68 silvacarl2 opened 3 months ago
0
is there a bench mark report for whisper large v3 model ?

#67 fastfading opened 3 months ago
0
Scripts for running WER benchmarks are missing

#66 stri8ed opened 4 months ago
0
In-memory audio input mode

#65 amdrozdov opened 4 months ago
0
Timeline has no milliseconds

#64 zx3777 opened 5 months ago
0
Why not use torchaudio.compliance.kaldi.fbank???

#63 BBC-Esq closed 4 months ago
1
initial_prompt for tensorrt backend

#62 draganjovanovich opened 6 months ago
1
Error using tensorRT-LLM as backend

#61 Wyswyss closed 6 months ago
1
Possible to run WhisperS2T without GPU? (Issue with CUDA)

#60 tlcameron3 closed 4 months ago
3
Randomly getting error while generating word timestamps

#59 rahulmate opened 7 months ago
4
how to convert a custom whisper in openai format or HF whisper model to TensorRT based backend ?

#58 StephennFernandes opened 7 months ago
21
Fix for small segments

#57 Pranjalya opened 7 months ago
5
'RuntimeError: stft input and window must be on the same device but got self on cuda:1 and window on cuda:0' when specify "device_index = 1" of "whisper_s2t.load_model"

#56 JH90iOS opened 7 months ago
1
Heuristics

#55 ngcheeyuan opened 7 months ago
0
Has this repository been abandoned?

#54 BBC-Esq closed 7 months ago
2
Non latin characters cannot get exported to files

#53 EricBizet closed 4 months ago
0
Non latin transcripts cannot be written to files

#52 EricBizet closed 4 months ago
2
[`large-v3`] Error during transcription: Invalid input features shape: expected an input with shape (3, 80, 3000), but got an input with shape (3, 128, 3000) instead

#51 twardoch opened 8 months ago
5
Handle batch processing when few files fails in the whole batch

#50 BBC-Esq opened 8 months ago
3
have you considered using the "hotwords" concept for newer terminology?

#49 BBC-Esq closed 7 months ago
2
problems with using huggingface flash attention 2 backend on windows

#48 BBC-Esq opened 8 months ago
0
setting cpu threads at runtime made easier/given as example?

#47 BBC-Esq closed 7 months ago
2
mismatch in compute_type when running on cpu

#46 BBC-Esq closed 7 months ago
1
word error rate mystique?

#45 BBC-Esq closed 7 months ago
1
community integrations portion of readme please?

#44 BBC-Esq closed 7 months ago
5
temp directory absolutely necessary?

#43 BBC-Esq closed 8 months ago
2
ffmpeg issue - semi-IMPORTANT

#42 BBC-Esq closed 8 months ago
11
running on macos without cuda

#41 appsmartsoftware closed 8 months ago
1
suppress or remove annoying print statement

#40 BBC-Esq closed 8 months ago
6
depricated flag for flash attention 2 with huggingface backend

#39 BBC-Esq opened 9 months ago
1
add quotation marks to prevent ffmpeg crashing with some file names

#38 MahmoudAshraf97 closed 9 months ago
1
SPEED TESTING; add speed tests here folks!

#37 BBC-Esq closed 8 months ago
1
Prompting causes crashes

#36 colinator closed 9 months ago
1
speaker diarization

#35 tristan-mcinnis opened 9 months ago
1
single sent in utt - txt writer

#34 shashikg closed 9 months ago
0
other backends such as whisper.cpp?

#33 BBC-Esq opened 9 months ago
7
Minor fixes and improvements

#32 shashikg closed 9 months ago
0
Added medium and medium.en models for TensorRT-LLM backend

#31 colinator opened 9 months ago
9
Please support whisper medium and medium.en in tensorrt-llm backend

#30 colinator opened 9 months ago
1
dependency conflicts, please help me use your library!

#29 BBC-Esq closed 8 months ago
11
way to install just ctranslate2 backend

#28 BBC-Esq closed 9 months ago
0