Comments (2)
Platform:::Linux lubancat 4.19.232 #12 SMP Fri Nov 10 10:22:31 CST 2023 aarch64 GNU/Linux
from faster-whisper.
@Hestinorwu , hello. Maybe your audio has too much hallucination so the model takes longer to process. Ex:
Processing audio with duration 01:48.553
Processing segment at 00:00.000
Compression ratio threshold is not met with temperature 0.0 (4.642857 > 2.400000)
Compression ratio threshold is not met with temperature 0.2 (4.187500 > 2.400000)
Compression ratio threshold is not met with temperature 0.4 (18.111111 > 2.400000)
Compression ratio threshold is not met with temperature 0.6 (5.089552 > 2.400000)
Log probability threshold is not met with temperature 0.6 (-1.003701 < -1.000000)
Log probability threshold is not met with temperature 0.8 (-2.498282 < -1.000000)
Log probability threshold is not met with temperature 1.0 (-4.083577 < -1.000000)
Reset prompt. prompt_reset_on_temperature threshold is met 1.000000 > 0.500000
Processing segment at 00:10.420
[0.00s -> 8.00s] Qasid'aq Al-Maraham
[8.00s -> 10.42s] Iqul
Compression ratio threshold is not met with temperature 0.0 (14.322581 > 2.400000)
Compression ratio threshold is not met with temperature 0.2 (24.470588 > 2.400000)
...
Could you show your log and attach your example audio ?
from faster-whisper.
Related Issues (20)
- Deleted
- FYI: FUTO did an ACFT finetune of whisper that works with <30s of audio
- Issues with pip package (missing attribute detect_language_multi_segment)
- [bug] distil-small conversion results in junk! HOT 1
- Could not locate cublasLt64_11.dll
- Possible to abort transcription? HOT 1
- Very bigger segment (chunk) size (almost 30 second each) with BatchedInferencePipeline HOT 4
- Choice of model output langauge of easiset way to do that?
- [Hallucinations] Repetition of words or chunks with own fine-tuned model
- faster-whisper vs whisper: PyAV stops during decode, ffmpeg continues HOT 2
- Duplicate sentences and missing sentences in large-v3
- a simple web-ui for whisper
- Cyrillic letters in Polish transcription
- Memory on GPU not cleared after transcription HOT 4
- Fair Benchmarking of Faster-Whisper - Parameter equivalents to Hugginface HOT 2
- CUDA failed with error an illegal memory access was encountered
- An amazing bug that importing fast whisper conflicts with git
- Bug - "No active speech found in audio results" HOT 1
- Is docker image `nvidia/cuda:12.2.2-cudnn8-runtime-ubuntu22.04` more suitable than `nvidia/cuda:12.0.0-runtime-ubuntu22.04` for faster-whisper's cudnn requirements?
- Deploy faster-whisper as a native web-app.
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 faster-whisper.