-
STT로 텍스트 데이터 변환 이후, NLP 엔진을 돌릴 강의 영상 데이터의 선정에 있어서 논의 사항이 있습니다.
현재 고민 중인 안건은 총 두 가지로, MVP 구현 등에 있어 더욱 효율적인 방안을 찾고 있습니다.
첫번째 안건은 기존 아키텍처 설계 그대로 실제 강의 영상 파일을 input해 DB에 저장한 다음, 음성을 추출해 데이터로 저장하고, 해…
-
Greetings, how i can use model to recognize speech to text, like from wav/mp3/mp4 file and record all speech to file? probably it can to make time stumps like in srt files
-
To quote @joshwlambert:
> If you are happy with this as an ongoing plan please let us know. The
code to be reviewed for our work is:
DAISIE_sim_constant_rate
DAISIE_sim_constant_rate_shift
DAIS…
-
Does the sources of an Open AI model also need to be open in order to comply with the standard?
A couple of real examples:
* Voice recording from children used for training a speech-to-text (STT…
-
It would be nice to have a service that allows using the voice recognition script for Asterisk that uses Google's Cloud Speech API, in which the recognized voice would be stored in a sensor of the hom…
-
I am trying the newest code and the provided demo data. There is no error when the spatial downsampling factor was set to 1, but the program only identified 33 neurons (your attached "demo_visualizati…
-
The vosk model contains a vocabulary list:
https://raw.githubusercontent.com/parolteknologio/stt-esperanto/master/vosk/common-voice-corpus-7/vosk-model-small-eo-0.22/graph/words.txt
It contains no…
-
Based on this Pull Request: https://github.com/jasperproject/jasper-client/pull/439
That would allow us to interact with Naomi using basic HTTP requests
-
```
What steps will reproduce the problem?
1. Set AutoUpdate to true for a DataItem within the project
2. Start up STT#
3. Check out the the TimeControoler widget for that DataItem
What is the expect…
-
MicrosoftのminiサイズのLLM。
https://huggingface.co/microsoft/Phi-3-mini-4k-instruct