-
Dears,
I can finetune with m4t_finetune in SPEECH_TO_TEXT mode successfullty.
However, when I finetune in --mode TEXT_TO_SPEECH and SPEECH_TO_SPEECH, the script will throw error "NotImplementedEr…
-
This is a task to do a spike (limited time to do research) on speech recognition and see how good it can be running on local device. It would be neat to have "Search with your voice" capability like Y…
-
# Task Name
Multilingual Speech to Speech Translation (s2st): converting speech from one language directly into speech in another language. This task requires the model to have strong multilingual …
-
-
# Task Name
Speech Summarization of long speech input that can be even longer than 30 minutes.
## Task Objective
Speech Summarization refers to the task of generating a text summary from a gi…
-
`torchaudio` is an extension library for PyTorch, designed to facilitate audio processing using the same PyTorch paradigms familiar to users of its tensor library. It provides powerful tools for audio…
-
Hi. I am trying to understand you approach and I still don't quite see how alignments are done for unrelated text and speech corporas. Could you please explain that and point out the files in the code…
-
# Speech Separation
Speech separation is the task of obtaining clean, single-speaker speech from a speech mixture of multiple overlapping speakers.
## Task Objective
**Why is this task needed…
-
Hi! I really love the new voice option in 1.1.1! Thanks for writing it.
The speech recognition works very well, it recognises my prompts quickly. But the responses are not played back. Perhaps it's…
-
# Multi-Lingual Speech Recognition
## Task Objective
Automatic Speech Recognition (ASR) is the task to transcribe the content of speech into text. In this multi-lingual ASR task, our objective i…