fairseq

fairseq copied to clipboard

Repetitions are generated although no_repeat_ngram_size is activated

1

## 🐛 Bug Commit 8ca4813 introduced a bug in ngram_repeat_block.py. An argument no_repeat_ngram_size does noes not block repetitions ### To Reproduce Generate longer texts. Repetitions occur. #### Code sample I...

vladsolovyev

# Before submitting - [V] Was this discussed/approved via a Github issue? (no need for typos, doc improvements) - [V] Did you read the [contributor guideline](https://github.com/pytorch/fairseq/blob/main/CONTRIBUTING.md)? - [V] Did you...

androstj

## ❓ Questions and Help Can we use this for multilingual ASR? like in a single audio if there r say 2 languages and we can differentiate it n it...

DreamyPujara

Update README.md

1

# Before submitting - [ ] Was this discussed/approved via a Github issue? (no need for typos, doc improvements) - [ ] Did you read the [contributor guideline](https://github.com/pytorch/fairseq/blob/main/CONTRIBUTING.md)? - [...

asr-pub

## 👉 [Please follow one of these issue templates](https://github.com/pytorch/fairseq/issues/new/choose) 👈 Traceback (most recent call last): File "/home/hgc/miniconda3/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 69, in _wrap fn(i, *args) File "/samsung/hgc/fairseq/fairseq/distributed/utils.py", line 362, in distributed_main main(cfg,...

HSunshine99

[Wav2Vec2] Wav2Vec2Conformer Fine-Tuned seems to give Gibberish on Librispeech example

11

## 🐛 Bug Wav2Vec2's newly released fine-tuned conformer checkpoints (see [here](https://github.com/pytorch/fairseq/tree/main/examples/wav2vec#pre-trained-models)) don't produce reasonable results on an example of Librispeech. I'm not sure if the model requires a different ###...

patrickvonplaten

Cannot find task 'translation_speech_length'. I am following: [https://github.com/microsoft/NeuralSpeech/tree/master/VideoDubber](https://github.com/microsoft/NeuralSpeech/tree/master/VideoDubber)

fadone

wav2vec2 inference simple process

4

## 🚀 Feature Request Provide a simple inference process/pipe for the wav2vec 2.0 model. ### Motivation Current inference script examples/speech_recognition/infer.py handles a lot of cases, resulting being extremely complex. ###...

elisonlau

The 'label_smoothed_cross_entropy_with_rdrop.py' file has a bug, preventing validation.

1

## 🐛 Bug There is a bug in the label_smoothed_cross_entropy_with_rdrop.py file that causes an abnormality in the sample, leading to an array index out-of-bounds exception during validation. Specifically, in the...

xyb314

data not found

2

## 📚 Documentation can't find dataset "preprocessed WMT'16 En-De data provided by Google." 404 not found: Thanks!

fkjslee