-
Why is the quality of `stable-ts` transcription much worse than that of `openai/whisper`? New lines of text are added where they should not be, numbers like `0.003` and `0.05` are defined as `0 0 3` a…
qo4on updated
11 hours ago
-
# Task Name: Text-to-Audio Generation
The task aims to generate general audio based on the given holistic text description.
## Task Objective
The primary goal of the Text-to-Sound (TTA) Gener…
-
**Description**:
We currently have news full audio and corresponding news transcript. We would like to get the news text and audio data split into segments to train our STT and TTS model.
**Implemen…
-
To the Microsoft Support Team,
We have been using ConversationTranscriber of the Azure Speech SDK, to implement Diarization in our project, and have encountered an issue in which we need your assis…
-
It's maybe not a bug but an inconvenience resulting in multiple similar tags being produced.
* `pipeline` value produced in
[monitor.AIProcessingError(err.Error(), pipeline, ...](https://github.co…
-
Add audio transcriptions to all episodes
* Ask HZ for written out texts --> not availble
* Generate texts via [Whisper AI](https://openai.com/index/whisper/) or similar speech-to-text software
-
**Parent ticket:** [Feature: Audio File Handling](https://github.com/marawanxmamdouh/ConvoNerd/issues/17)
### Description:
Implement a speech-to-text module to transcribe audio content into text.
…
-
The note in [WCAG 1.2.3](https://www.w3.org/WAI/WCAG21/Understanding/audio-description-or-media-alternative-prerecorded.html)
on the differences between text transcript and audio description is highl…
-
- **Package Name**: azure.communication.callautomation
- **Package Version**: 1.2.0
- **Operating System**: Ubuntu 20.24
- **Python Version**: 3.11
**Describe the bug**
The recordings that are …
-
I have a requirement to save the raw data sent to whatsapp to be recovered later on.
However, i just noticed that the ClientMessageRequest type has incomplete data structure, which means that text,…