During our work as speech technologists we developed additional software solutions for the work that often occur after "using ASR".
These various software packages are here described and made available for download.
LabelMaker: How to add lables to the transcripts?
CTMimprover: How to automatically improve the ASR-results in a CTM or SPK file.
ASRcorrector: How can I correct the mistakes within an automatically generated transcript?
ASRcorrector V2.8.32 and above, is a software program with various screens that allows you to correct the outcome of the ASR into a suitable text.
(last update: 19-9-2023)
|Please remember that development of ASRcorrector will be discontinued from 1 October 2023. ASRcorrector has the ability to use the recognition of various speech recognisers, but practice shows that this is no longer done. In our environment, it is mainly Whisper that is used as a recogniser and we will therefore continue with WhisperCorrector. Up to now, these two programmes are actually the same but we cannot guarantee that they will be so in the future.
We therefore recommend that if you need an update, you pick it up from WhisperCorrector below.
WhisperCorrector: How can I correct the mistakes within an automatically generated transcript with the OpenAI Whisper engine?
WhisperCorrector V1.0.0 and above, is a software program with various screens that allows you to correct the outcome of the Whisper ASR-engine into a suitable text. WhisperCorrector is based on (and still equal to) ASRcorrector. However, ASRcorrector has the option to include the ASR-results from various ASR-engines, while WhisperCorrector only deals with the results of the Whisper ASR-engine.
(last update: 19-9-2023)
Whisper Batch: Gives the possibility to select various files that need to be recognised.
Gives the possibility to select various files that need to be recognised, each with its own items like model, languages and other otems. Once selected all the files, you can start the process from this program. It works now for Windows 64-bit and MacOS.
A manual will be written in the near future after the first comments :-).
FromTo: How can I convert a ctm/spk file into subtitles and/or html-files?
FromTo V1.7 (and above) is our solution for this.
Once the ASR has been done, one can download the (timed) results. However, each ASR-engine seems to have its own set of output-formats. Sometimes you can get a special XML-file, sometimes a CSV-file and sometime something else. Moreover, if it is XML, each ASR-engine seems to use its own XML-schema.
So we wrote software that reads the (standard) output of the ASR-engines we support (a CTM-file), and transforms it into one of the following output formats:
- SRT: the standard subtitle format used by nearly all existing video and audio players (like VLC)
- VTT: the new internetversion of the SRT-format, used by all the modern browsers
- Karaoke: a html-file where each recognised word is "connected" with the audio-file and where clicking on a word results in playing the audio-file from that word. Words played, are highlighted.
- CHA: the format used in the CHILDES format.
FAcleaner: How to convert the text from the ASRcorrector into a good FA_text that can be run by a FA-conversion?
FAconvertor: How do I combine the corrected transcript with the CTM-file to generated a subtitle/karaoke style file?
FAconvertor is a software program that combines the corrected text (from ASR corrector) with the CTM-file (i.e. outcome of the FAconvertor-software). The outcome is a correct HTML-file (Karaoke), SRT-subtile file and text-file that can easily be converted into a MSword-file.
FAgluer: How do I combine two (or more) parts of an interview into one set of files?
To_WAV_Convertor: How do I convert audio or video files to WAVE files, a filetype which is often required by tools?
ToWave convertor is a software program for MacOS that allows you to convert various AV-files into a 16-16-1 wav-files (a 16kHz, 16-bit, mono).
K-Lite: I can't seem to play certain mp4-files on my PC. How do I fix this?