fairseq

fairseq copied to clipboard

wav2vec/unsupervised/scripts/prepare_timit.sh add root directory path to already added root directory path.

1

#### Do you guys even check code before adding to main branch? This is so frustrating and unexpected from meta's repo. --- When running the file in colab, `!zsh unsupervised/scripts/prepare_timit.sh...

ih7012

Learn new & fine-tune existing language pairs in NLLB

1

Hello team, Is it possible to: - fine-tune any language pair in a pretrained NLLB model; - learn an NLLB model for a new language pair, without the full retraining...

molokanov50

I’m also trying to reproduce the results, but the WER and UER are not satisfactory (I’ve been stuck for two weeks now) and would like to ask for your guidance....

XR1988

Help with replicating the results for wav2vec-u TIMIT

28

#### What is your question? I am trying to replicate the results for the new wav2vec-u (https://ai.facebook.com/research/publications/unsupervised-speech-recognition) model (currently working on TIMIT). However, it seems that using the default code...

JeromeNi

How to reproduce the WER score of Wav2vec-U

1

## ❓ Questions and Help #### What is your question? I have run the pipeline of wav2vec-U and trained a GAN on Librispeech 960h. When using Viterbi decoding, I can...

cywang97

wav2vec2-object of type 'NoneType' has no len()

2

## 🐛 Bug(I have seen all issue about this error. But My situation is different.) I follow the offical method (https://github.com/facebookresearch/fairseq/tree/main/examples/wav2vec) to use other datasets to fine-tune wav2vec_small_10m.pt. However, there...

L1xxer

Testing Textless S2ST with pre-trained models

6

Hello, I am trying to test the Textless S2ST model as mentioned [here](https://github.com/facebookresearch/fairseq/blob/main/examples/speech_to_speech/docs/textless_s2st_real_data.md). However, I encountered an error while running this line: `python examples/speech_recognition/new/infer.py \ --config-dir examples/hubert/config/decode/ \ --config-name infer_viterbi...

dina-adel

## ❓ Questions and Help #### What is your question? I wanted to make sure this is the correct way to use the VIDEOCLIP model. I have a basket video...

dnitti-psee

I've searched in the model's checkpoints on Hugging Face, but mms-tts-srp was not there. Is there any ongoing effort to add this? Even though [this](https://dl.fbaipublicfiles.com/mms/misc/language_coverage_mms.html ) paper says Serbian language...

gamisn

score calculation in translation_moe

1

## ❓ Questions and Help ### Before asking: 1. search the issues. 2. search the docs. #### What is your question? ``` for EXPERT in $(seq 0 2); do \...

zhmingzhaung