Resources

View closed (17)

Code switched audio

#58 opened about 2 months ago by

achyudev

Training on New Language

#56 opened 6 months ago by

alvynabranches

First word always missing in speech-to-speech translation (demo and API) – is this a known limitation?

#55 opened 7 months ago by

Serqanz

ASR (one language)

#54 opened 9 months ago by

Mylunaire

minimal HW requirements

👍 1

#52 opened about 1 year ago by

minarth

how to select speaker

#51 opened about 1 year ago by

7xN

Questions on the model capabilities and features

#50 opened about 1 year ago by

yevgeniyilyin

Inference with finetuned model (.pt format) which is created using the finetuning in github

#49 opened about 1 year ago by

ThivyanRR

Deployment on Self Hosted Inference servers like Nvidia Triton

#48 opened about 1 year ago by

mllearner0717

Performance and Stability

#47 opened over 1 year ago by

TeaCult

TextToSpeech in Ukrainian

#46 opened over 1 year ago by

Techn0man1ac

Is there a person in this desert who can answer me?

#45 opened over 1 year ago by

developeranalyser

T2TT finetuning

#44 opened over 1 year ago by

vipinkatara

Use TTS audios for commercial uses

#43 opened over 1 year ago by

Giutau

Update README.md

#42 opened over 1 year ago by

Sarchia

[AUTOMATED] Model Memory Requirements

#41 opened over 1 year ago by

model-sizer-bot

Customize model

#40 opened over 1 year ago by

developeranalyser

how can reduce GPU usage For FineTune ?

#39 opened over 1 year ago by

developeranalyser

Why ?

#38 opened over 1 year ago by

developeranalyser

.pth file

#37 opened over 1 year ago by

developeranalyser

FineTune Errror TEXT_TO_SPEECH Same lang

👀 1

#36 opened over 1 year ago by

developeranalyser

use orginal .pth or FineTuned .pth

#35 opened over 1 year ago by

developeranalyser

Error FineTune with GPU 40GB !!!!!!!!!

🔥 🚀 1

#34 opened over 1 year ago by

developeranalyser

Quantization

🔥 1

#33 opened over 1 year ago by

mehtameet2802

Evaluate ASR Examples using finetuned model checkpoint

#32 opened almost 2 years ago by

aalisha

License

👍 5

#31 opened almost 2 years ago by

nth-attempt

The model can't be downloaded

#30 opened almost 2 years ago by

JadwalAlmaa

Loading the model takes a long time using from_pretrained

#29 opened almost 2 years ago by

Zhaoz1997

ValueError: You must specify a `tgt_lang` to generate translated speech.

#28 opened almost 2 years ago by

alphatozeta

Real Time Translations..

#27 opened almost 2 years ago by

shuaiby88

How to add new language to dataset and retrain the existing model for the new language added?

#26 opened almost 2 years ago by

Diyapiu

Translation of longer texts

🔥 1

#25 opened almost 2 years ago by

hanshupe

Mandatory ressources for seamless-m4t-v2-large on production

#24 opened almost 2 years ago by

Stephane1

translated text is not complete

#21 opened almost 2 years ago by

Nathan-Geo

Timestamps tagging in ASR and S2TT

#20 opened almost 2 years ago by

Haseebraja

Anyone knows how to translate longer text? - I am new on this

👍 1

#18 opened almost 2 years ago by

JaimeLugo

[Help Wanted] facebook/seamless-m4t-v2-large does not support the traditional Chinese language (cmn_Hant).

#17 opened almost 2 years ago by

ZoneTwelve

Show examples using "torchaudio.save" instead of "scipy.io.wavfile.write" in README

#16 opened almost 2 years ago by

abellion

TTS colab and streamlit repository

#15 opened almost 2 years ago by

macadeliccc

Use in SageMaker

👍 1

#13 opened almost 2 years ago by

joehoyle

asr fleurs word error rate

👍 4

#4 opened almost 2 years ago by

joujiboi