ufal / whisper_streaming

Whisper realtime streaming for long speech-to-text transcription and translation

ufal/whisper_streaming Issues

[CONTRIBUTION] Speech Dataset Generator
Updated 4 months ago
Would a PR to change print statements to logging.debug be accepted?
Updated 4 months ago
batching inference and forced decoding for speedup and multi-target
Updated 4 months ago9
Thesis Error
Closed 4 months ago1
Using VAD
Closed 4 months ago7
language detection
Closed 5 months ago1
Voice Activity Controller
Updated 5 months ago5
speech can not be handled after some silence for a while or some different languages
Closed 5 months ago6
Using Whisper API instead of local offline Whisper model,
Closed 5 months ago6
Any Idea for feature update for targeted speaker transcription?
Closed 5 months ago3
For real-time transcription, crashes after loading around the 60 sec market.
Closed 5 months ago2
macOS support
Closed 6 months ago20
I stop receiving predictions while streaming after some time
Closed 6 months ago3
Custom HuggingFace tokenizer with faster-whisper
Closed 6 months ago11
windows opus-fast-mosestokenizer installation
Closed 6 months ago6
large-v3 model
Closed 6 months ago2
youtube m3u8 use whisper streaming?
Closed 6 months ago1
Always chunking because of len
Closed 6 months ago4
batching multi-client server
Updated 7 months ago3
It seems like opus-fast-mosestokenizer is not supported in windows
Closed 7 months ago2
Keep recieving transcription text from the server even after I mute my mic/stop transmitting
Closed 7 months ago2
Client sample in python.
Closed 8 months ago2
Why the OnlineASRProcessor.commited is always incremented?
Updated 7 months ago2
whisper_online.py returns only 'Python'
Closed 7 months ago1
export LD_LIBRARY_PATH when nvidia-cudnn-cu11 is installed via pip in the venv
Closed 7 months ago1
Import error when using `whisper_online` as module
Closed 7 months ago5
VAD and whisper-timestamped
Closed 7 months ago3
Running whisper_streaming with a fine-tuned whisper model
Closed 7 months ago9
How did you measure computationally unaware latency?
Closed 7 months ago5
'str' object has no attribute 'sep'
Closed 7 months ago2
Enable translate to any language
Closed 7 months ago4
whisper_online_server.py not producing a correct text
Closed 7 months ago2
Usage Real Time Speech to Text
Closed 7 months ago1
Error while online.process_iter()
Closed 9 months ago2
can it transcribe in real-time?
Closed 7 months ago1
Does this only take pre-recorded audio or can it transcribe microphone input?
Closed 8 months ago1
whisper_online_server.py Freezes after few seconds
Closed 8 months ago2
[BUG] AttributeError: 'MosesTokenizer' object has no attribute 'split'
Closed 10 months ago3
Is this workable for fastapi?
Closed 8 months ago2
whisper_online_server Processing Error
Closed 8 months ago
BUG ImportError('libmosestokenizer-dev.so: cannot open shared object file: No such file or directory')
Closed 9 months ago3
opus-fast-mosestokenizer can't support windows,so this can't run on windows.
Closed 9 months ago3
How to run model inference from mic on windows
Closed 9 months ago1
How can i do inference on microphone
Closed 9 months ago1
Usage as Fronteend+Backend app with websockets
Closed a year ago3
Review a demo paper
Closed a year ago
Real-time input from microphone
Closed a year ago1
Requesting en-demo16 file for running example
Closed a year ago3
server <- sounddevice and read from real time mic
Closed a year ago3