Comments (3)
You can now output the results to multiple file formats. For example:
./main -m models/ggml-tiny.en.bin -f samples/jfk.wav -otxt -ovtt -osrt
will generate .txt
, .vtt
and .srt
files.
Also, you can now redirect the results with >
, as suggested by @aufziehvogel
from whisper.cpp.
I use redirection with >
and for me it works without problems.
Maybe you're experiencing buffering? Shell redirection to my knowledge by default uses output buffering, i.e. you will not see data as it is written by the program. Instead, data will be written to the file whenever there (according to the buffering implementation) is enough data.
You can change the buffering with stdbuf
. For example, to write to the file once per line you could call:
stdbuf -oL ./main -m models/ggml-large.bin -f input.wav > output.txt
One useful option imo would be to get the output without all model loading info (lines starting with whisper_model_load:
and main:
). Imo, the model loading info could be written to stderr, because it is intended for human readers, while the actual detections could go to stdout. Then a normal redirection with >
would still output the model loading info on the screen.
from whisper.cpp.
Yeah, I thought it's related to buffering, too, @aufziehvogel. I think I waited for quite a while, though, and yet nothing showed up. Anyhow, thanks for letting me know about stfbuf
, that fixed it!
Thanks, @ggerganov!
from whisper.cpp.
Related Issues (20)
- `models/download-coreml-model.sh` didn't work
- Docker "no matching manifest for `linux/arm64`"
- `make stream` failed because of the problem of ‘SDL_HINT_AUDIO_RESAMPLING_MODE’ was not declared in this scope
- Undefined symbols for architecture arm64: "_MTLCopyAllDevices" HOT 1
- Problem creating node addon HOT 2
- [Feature Request] Any plans for translation using OpenAI instead of DeepL? HOT 1
- Feature request - Support WhisperSpeech for voice generation with whisper model HOT 1
- Problem compiling addon.node (+solution) HOT 7
- ci: windows-msys2 CLANG64 builds are failing HOT 1
- CPU Performance Regression? (Older version much faster) HOT 13
- ci: emscripten builds are failing with Emscripten SDK 3.1.58 HOT 1
- Stream: noise ouput
- Spam Attack HOT 2
- Ubuntu 22.04 - tested commit 8fac645 - microphone is not passing audio to talk-llama , older builds ( from a month passing microphone audio ) HOT 2
- MSVC static runtime library
- The path to metal files is not validated when whisper.cpp is used as a subproject
- Disabling WHISPER_LOG_INFO HOT 2
- Unable to generate the large-v3 CoreML model
- chinese characters not showing up on windows HOT 2
- When transcribing Chinese audio, using whisper_full_get_segment_text can return the correct text, but using whisper_full_get_token_text might result in NULL.
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from whisper.cpp.