-
Hi,
As written in the title, how can we run model training, e.g., wav2vec2.0, from the python file instead of via CLI? My use case is that I want to understand the data flow and training details, s…
-
-
Why does this error occur?
preprocess.py: error: unrecognized arguments: --src-dict /home/sgh/project/RenewNAT/data/v15news/dict.source_language.txt --tgt-dict /home/sgh/project/RenewNAT/data/v15new…
wyabo updated
5 months ago
-
## 🐛 Bug
### To Reproduce
Steps to reproduce the behavior (**always include the command you ran**):
1. Run cmd 'pip install --editable ./'
2. See error
```
/usr/bin/clang -Wno-unused…
-
Nice implementation first!
when reading your code ConvDecoderFairseqBS, in each step(), beam_search will select new top K beams, but the inputs to next step is just replace this time step's padded …
-
are all the required preprocessing steps:
1. acquire dataset, checkpoint, source
2. train spm
3. hubert feature extraction
4. run fairseq
or are there any missing parts?
-
## Steps to reproduce
I am trying to use the RoBERTaNERTask for NER task. So I ran `pytext gen-config RoBERTaNERTask` to generate default config file and twinkle it with personal settings. With the…
-
How to get source language detection.
This should be similar to [detect_language function in whisper](https://github.com/openai/whisper/blob/main/README.md#:~:text=Below%20is%20an%20example%20usage%2…
-
Hi, thanks for your great work! I'm trying to export AV-HuBERT model (.pt format) to .onnx format like this:
```python
models, saved_cfg, task = checkpoint_utils.load_model_ensemble_and_task([cfg.co…
-
I tried to run the predict_hallucination_mt.py file by downloading the pre-trained xsum model. But when,
xlmr = XLMRModel.from_pretrained(
model_path,
checkpoint_file='checkpoint.pt'
…