Stack Overflow
Stack Overflow

Questions tagged [whisper]

Whisper is one of the components of Graphite, and is responsible for the back-end storage of incoming metrics from the network.

Whisper is one of the components of Graphite, and is responsible for the back-end storage of incoming metrics from the network.

Whisper is a fixed-size database, similar in design and purpose to RRD (round-robin-database). It provides fast, reliable storage of numeric data over time. Whisper allows for higher resolution (seconds per point) of recent data to degrade into lower resolutions for long-term retention of historical data.

57 questions
0
votes
0 answers

Using OpenAI Whisper terminates immediately after running

Been searching the internet for a few days to find a fix but was unable to. I have a fresh linux install (Arch) and fresh install of both pytorch and whisper, yet when I try to use whisper on an audio file I get an error. $ whisper…
Ivailo Hristov
  • 25
  • 1
  • 6
0
votes
0 answers

Keep getting 400 Invalid File Form error from Whisper API

I am trying to call Whisper API from my android app. I am recording the audio and storing in .wav format. when i am calling the whisper API its always giving me 400 error saying invalid file format. I tried playing the audio back and its working.…
Manoj ahirwar
  • 1,062
  • 1
  • 10
  • 24
0
votes
0 answers

TypeError: Whisper.forward() missing 1 required positional argument: 'tokens' when creating chatbot with fine-tuned model

On google colab I am creating a chatbot, using whisper to transcribe an audio then generate response, based on a fine-tuned model. I use the model with pure-text chatbot first, and it works fine, but when integrating whisper, it give me the…
resssslll
  • 65
  • 1
  • 7
0
votes
1 answer

Why is my streamlit app not correctly summarizing my mp3-transcription?

I'm working on a Streamlit app that processes MP3 files. The main steps include: Uploading an MP3 file. Splitting the audio into smaller chunks using pydub. Transcribing these chunks using OpenAI. Summarizing the transcriptions using transformers…
Patrick Schmidt
  • 1
0
votes
0 answers

Whisper .net in .Net 4.7.2 is not able to transcribe audio

I am using whisper .net in ASP.NET Core 6 and its working fine there, but i also want to apply same approach on .Net 4.7.2 , but i am not able to transcribe data. Whisper use IAsyncEnumerable type for its processor and its feature does not have…
Hamza Hamid
  • 3
  • 3
0
votes
0 answers

Installation of package '.../audio.whisper_0.2.1.tar.gz' has a non-zero exit status

Good afternoon everyone! I am trying to install audio.whisper package in R. I have done everything according to the instructions: remotes::install_github("bnosac/audio.whisper", ref = "0.2.1") I got an error, because remotes library was not…
prolabrus
  • 1
  • 1
0
votes
0 answers

problems with torchmetrics import while trying to import whisperx

I'm trying to import whisperx to my colab notebook. I already installed the package, and it worked well, until I made some changes to the notebook (that I cannot trace back, but I guess other packages downloads). Now I am having the following error…
PmN
  • 43
  • 1
  • 4
0
votes
1 answer

Whisper based speech to subtitles python script - word timestamps issue

Hello I'm writing a python script that takes a mp4 file in output and outputs a WEBVTT file of the transcription. I managed to make it work, but now I'm trying to reduce the size of each subtitle lines and get closer to word-level transcriptions in…
maximeb
  • 1
0
votes
1 answer

whisper-merge appears to replace rather than aggregate duplicate values

I'd like to use whisper-merge to merge two whisper databases using an aggregation method, but it appears that one piece of data replaces the other if there's any overlap of timestamps. Obviously graphite itself can aggregate data, but does anyone…
Karl von Randow
  • 474
  • 3
  • 13
0
votes
1 answer

graphite storage schema retention

I have a question: I would like to keep whisper data for 1 year (7 days 5 seconds, 30 days 1 minute, 1y 5 minutes) Is this correct: [default] pattern = .* retentions = 5s:7d,1m:30d,5m:1y How long will my data be kept? 1 year ? or (7d+30d+1y)…
mymarcelsql
  • 11
  • 3
0
votes
0 answers

Alternatives to whisper database

I am using graphite + whisper for monitoring the system metrics but since the number of metrics are increasing , it is becoming difficult to use whisper as a storage as it is not an optimal solution because of inode table bottleneck and also it is…
Bharat Rawat
  • 41
  • 1
  • 3
0
votes
1 answer

How to store data in Graphite with retention of 100ms?

I am using graphite to display our application stats. storage-schemas.conf [stats] pattern = ^stats\. retentions = 1s:1h,1m:1d,1h:100d storage-aggregation.conf [stats] pattern = ^stats.* xFilesFactor = 0 aggregationMethod = sum Per second I am…
Nishanth Duvva
  • 665
  • 8
  • 18
0
votes
1 answer

what is default db of graphite

I have read that Whisper db is the default db which graphite uses to store metrics. Default Graphite setup consist of whisperDb Ref this. However i recently got confused to know that graphite-web uses sqlite db by default(Ref: this). Please reply…
Laxmikant
  • 1,551
  • 1
  • 13
  • 30
0
votes
1 answer

High volume write to graphite database with ms seconds delay

I have 5000K devices which ones are reading data from sensor 20 times in second. I'm pushing all data to kinesis but I want to make it queryable So I'm thinking to pool data from kinesis and store in Graphite. I will have a lot of write and not…
user8339772
  • 1
  • 2
0
votes
2 answers

graphite vs collectd. retentions not applied

I have installed collectd on BIND9 hosts and configured it to pass metrics to graphite. I want to be able to view metrics for at least 1 month but retentions in storage-schema.conf not applied for collectd section, and applied last default section…
0xDEAD BEEF
  • 1
  • 2
1 2
3
4