-
For translation quality estimation of Blaser 2.0, I think there is no limitation of the text (or the speech) length. However, from my personal perspective, I do not think the estimation will be accura…
-
The movie voice is in Chinese, I want to convert and output English subtitles, but after checking the translation and selecting English, I always get this message
The translate feature translates s…
-
- Paper: https://arxiv.org/abs/2201.11391 (3 languages: English, Sanskrit, Bengali)
- Git Repo: https://github.com/frozentoad9/CMST
- Original data source: https://vanimedia.org/wiki/Multi-language_…
-
## ASR
- [ ] ASR2K: Speech Recognition for Around 2000 Languages without Audio https://arxiv.org/abs/2209.02842
- [x] Whisper: Whisper is a general-purpose speech recognition model. https://github…
-
I was looking ove rthe implementation of you text to speech model. Is it working fine and if it is working then from where can I test It.
Thanks in advance.
-
# Dialect-to-Standard Normalization
The goal of this task is to evaluate to what extent speech models encode dialectal variation, by prompting models to normalize dialectal variants of Swiss German…
-
### Description
[Speech Note](https://github.com/mkiol/dsnote) is an app for note taking, reading and translating with offline Speech to Text, Text to Speech and Machine Translation. It includes fo…
-
Make job submission a two-step process for all scripts that have both a "stylesheet" and a "stylesheet-parameters" option. In addition to the [braille scripts that already have a two-step job submissi…
-
**Describe the bug**
A call to `SpeechSynthesizer.StopSpeakingAsync()` does not stop synthesis for a very long time, up to 30 seconds. The log file is here: [speech.log](https://github.com/Azure-Sa…
-
## 🐛 Bug
I am trying to use the model that you shared [here](https://dl.fbaipublicfiles.com/joint_speech_text_4_s2t/iwslt/iwslt_data/checkpoint17.pt) to generate translations for the speech that I …