fairseq

fairseq copied to clipboard

Need help in running prepare_text.sh for Wav2Vec2-U

1

My Task: Reproducing the results of Wav2Vec2-U for LibriSpeech 960h Corpus: I have created the train/valid/test.tsv files, for example: /path/to/data/ 3764-168670-0031.wav 131840 8455-210777-0060.wav 113200 7902-96592-0047.wav 74160 237-134500-0009.wav 35520 Next, removed...

Nemesis-19

FileNot Found error

2

**### Why am i getting this error** File "examples/speech_recognition/new/infer.py", line 499, in cli_main() File "examples/speech_recognition/new/infer.py", line 495, in cli_main hydra_main() # pylint: disable=no-value-for-parameter File "/home/hp/miniconda3/envs/test_fairseq_textless/lib/python3.8/site-packages/hydra/main.py", line 32, in decorated_main _run_hydra(...

Maverick7t

Hi there, For hubert pretraining, the data preparation guide [here](https://github.com/facebookresearch/fairseq/tree/main/examples/hubert/simple_kmeans) indicates that a kmeans model should be trained on each of the train and valid data and should be used...

amadeusuzx

assert step < max_len, f"{step} < {max_len}" AssertionError: 60 < 60

2

When I was training a summarization model under fairseq, I encountered the following error in the validation step. How can I solve this problem. -- Process 1 terminated with the...

sevensix617

Importing `hydra.experimental` results with an ImportError

1

Hey! Firstly, thanks for creating and maintaining the package! In my project I use both `fairseq` & `hydra` (hydra-core) packages. Importing hydra's experimental components results with an ImportError while using...

SagiPolaczek

README.glue.md GLUE Preprocess script is incorrect.

8

## What does this PR do? The script for running fairseq-hydra-train is incorrect and uses the invalid flag -config-dir. Fixed it to the correct flag --config-dir. ## PR review Anyone...

adithya-gv

Update README.md

2

#5423 issue dataset link is updated # Before submitting - [ ] Was this discussed/approved via a Github issue? (no need for typos, doc improvements) - [x] Did you read...

Akash-Vijaysingh-Shekhavat

Installation Error: M1 Mac

1

## 🐛 Bug Installation of latest release at the time i.e v0.12.2 ### To Reproduce Steps to reproduce the behavior (**always include the command you ran**): 1. pip install fairseq...

vandit2209

## 🚀 Feature Request TTS support for cmn ### Motivation I'd like to try the TTS for cmn and compare it with NVIDIA Riva, Flytech, and Alibaba TTS etc. ###...

JustinQiu

UST - KMeans Clustering & Acoustic Model(s) Missing

1

Hello fairseq team! #### Problem Summary I've been trying to reproduce the results of [this paper](https://research.facebook.com/publications/hokkien-direct-speech-to-speech-translation/) for research, and I believe there are some necessary model files / urls that...

mdconaway