fairseq

fairseq copied to clipboard

raise FileNotFoundError("Dict not found: {}".format(args.data))

1

2024-02-29 19:02:44 | INFO | fairseq_cli.generate | {'_name': None, 'common': {'_name': None, 'no_progress_bar': False, 'log_interval': 100, 'log_format': None, 'log_file': None, 'tensorboard_logdir': None, 'wandb_project': None, 'azureml_logging': False, 'seed': 1, 'cpu': False,...

guo-chuanchuan

Can I use [Roberta-base](https://huggingface.co/FacebookAI/roberta-base) for custom "Named Entity Recognition(NER)"? I have my own dataset which is tagged for a custom entity. I already used roberta-base for NER using Spacy.

Project-NSE

How to get video features in VideoCLIP without any access to captions

2

For `VideoCLIP`, how do we get the video encoder features without access to any captions. The default code at https://github.com/facebookresearch/fairseq/blob/main/examples/MMPT/README.md results in `MMBertForEncoder` as the final video encoder and it...

learn2phoenix

issue numpy when try to TTS method

1

 when i try use TTS method in google colabs in step 3. Load the checkpoint i have this problem. i wanna use fas.lang for farsi/ persian language...

changizyv

Wrong results when running inference with pytorch and MPS backend

1

just writing little code as the issue is very easy to recreate `device_gpu = torch.device("mps") ` `model = bundle.get_model(with_star=False).to(device_gpu, non_blocking=False) ` `with torch.inference_mode(): ` ` emission, _ = model(waveform.to(device_gpu)) `...

tonytorm

Hi, I have a fairseq translation model that I'd like to ship with a tauri or electron app for local inference. I have been able to run cloud inference through...

kabyanil

Update huffman_coder.py

1

bitarray doesnt support util, util.rindex() -> index(,right=1) # Before submitting - [ ] Was this discussed/approved via a Github issue? (no need for typos, doc improvements) - [x] Did you...

balaramas

[Wav2Vec2-XLSR-53]Problems about the pretrained model

2

Hi, when I tried to use wav2vec2.0 using transformers following the under lines under the Linux system: from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor #load pretrained model processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-xlsr-53-espeak-cv-ft") model =...

scutcsq

Can I use the wav2vec2 base model to train my own dataset which is of 8000 sample rate?

5

Can I use the wav2vec2 base model to train my own dataset which is of 8000 sample rate? Kindly help me out? also if yes then how much data do...

nome2050

**nllb 3.3B** translate from Chinese to Korean got: , , , , , , , , , , , , , , , **source_text**: 哈哈哈哈哈 说的什么玩意儿呀 这个声音太尖了 耳朵有点受不了哎 t**ranslated_tex**t: ,...

micronetboy