fairseq

fairseq copied to clipboard

## 🐛 Bug [Example notebooks](https://colab.research.google.com/github/facebookresearch/fairseq/blob/main/examples/mms/tts/tutorial/MMS_TTS_Inference_Colab.ipynb) for `meta-mms` on Google CoLab fail to import the `data_utils` library required for loading text to audio. ### To Reproduce Run cell 3. "Load the...

kaizengrowth

I would like to know if it is possible for the model to learn the features of a custom speaker from a sample audio and use that to generate an...

AvisP

Update hub_utils.py

1

fix bug for print_alignment # Before submitting - [ ] Was this discussed/approved via a Github issue? (no need for typos, doc improvements) - [ ] Did you read the...

tonylekhtman

## ❓ Questions and Help ### Before asking: 1. search the issues. 2. search the docs. #### What is your question? #### Code #### What have you tried? #### What's...

notbad6

Error when installing fairseq

6

Hi everyone, I am running into the following error when trying to install fairseq pip install fairseq This is the error in question : FileNotFoundError: [Errno 2] No such file...

ChristopheYe

Has anyone got the MMPT example to work?

1

## 🐛 Bug I am running into so many dependency errors when trying to use VideoCLIP model. If anyone has gotten it to work please share your details on which...

qingy1337

Although the paper states TTS is available for Slovak, there is no slk file in dl.fbaipublicfiles.com/mms/tts/slk.tar.gz

userghubhub

İs there a way to skip some words in translation, I tried to wrap some words with some placeholders $$$skipping words$$, I also tried to creat enumerated placeholders so that...

ekmekovski

NLLB is unable to translate into a complete long sentence in Chinese.

1

## 🐛 Bug Hi, I tried to test nllb for translating some English sentences to Chinese, and all my sentences are less than 60 tokens. However, most of sentences which...

logicvv

ValueError: offset must be non-negative and no greater than buffer length

5

Hi, I'm training the fairseq with the following script and get the error ValueError: offset must be non-negative and no greater than buffer length. fairseq-train data-bin --arch transformer \ --max-epoch...

LiYixuan727