fairseq

fairseq copied to clipboard

Hi, Is there a way to use a fine-tuned version of NLLB-200-distilled-1.3B model for translation from English to Canadian French and use it in production for a fin-tech firm in...

nohaelprince

how to prepare multitask data in speech to speech

1

I am training a speech-to-speech translation for French to English lang. Could anyone pls help me to do multitask training. Followed the below link to do multitask training (https://github.com/facebookresearch/fairseq/blob/100cd91db19bb27277a06a25eb4154c805b10189/examples/speech_to_speech/docs/direct_s2st_discrete_units.md) Used...

Saravinnai

Hello NLLB/fairseq team, I’m reaching out to explore how to fine-tune the NLLB model to support better Punjabi, a vibrant language spoken by over 100 million people worldwide, including a...

braghome

I tried to get a text back from the speech I generated using this model, but the text was a bit of. So maybe having some type of test could...

icnahom

I wanted to ask if there is a way for developer to simply call an http endpoint like Google or Azure TTS Service. If it's not planned, you guys should...

icnahom

[RFC] Multi-Channel Conv FeatureExtractor — Non-Audio Sensor → wav2vec2 Front-End

1

1. Purpose (Why) Research and practical demand for few-shot silent-speech, BCI, and multimodal ASR is soaring. The current fairseq wav2vec2 front-end assumes monaural audio waveforms (1 ch, 16 kHz) only,...

supernaiter

Update data_cfg.py

1

add @property to def standardize_audio(self) -> bool ## What does this PR do? Here is a bug with the function. when we call `self.cfg.standardize_audio`, it always return true. see https://github.com/facebookresearch/fairseq/blob/main/fairseq/data/audio/speech_to_text_dataset.py#L244-L248...

ajkpix

Could you please provide the finetune config files for the base and large versions of data2vec 2.0 for audio? #### What's your environment? - fairseq Version (e.g., 1.0 or main):...

rxhmdia

## ❓ Questions and Help ### Before asking: 1. search the issues. 2. search the docs. #### I want to use this model "nllb-200-distilled-600M" in an application lets say an...

sushanttwayana

no module found error

1

## 🐛 Bug I get a no module found error: commons ### To Reproduce Steps to reproduce the behavior (**always include the command you ran**): 1. I ran the comand...

dnabanita7