diff --git a/README.md b/README.md index 24cbec7ec0172f07e6bc32390e2429b5b0144779..a3a8681e3b4fa52d390d76dc1dc79af0bd91f2ca 100644 --- a/README.md +++ b/README.md @@ -71,7 +71,7 @@ conda activate speechcodebookanalysis The file ```conda.sh``` is sourced at the beginning of ```run.sh```. -### Fairseq Repository +### Fairseq Repository (as of 27th July, 2023) You need to clone the fairseq repository to another directory (e.g., ```../fairseq```). ``` @@ -80,7 +80,7 @@ git clone https://github.com/facebookresearch/fairseq.git Make sure to modify the file ```path.sh``` in order to export the necessary environment variables. The file ```path.sh``` is also sourced at the beginning of ```run.sh```. -### Model File +### Model File (as of 27th July, 2023) **You need to download and store a model file**. In the main script (```run.sh```) you can specify the ```model_path```. This study is based on the large pretrained model **XLSR-53** which can be downloaded here: [wav2vec2](https://github.com/facebookresearch/fairseq/blob/main/examples/wav2vec) **Unfortunately loading/initializing the model with version ```fairseq 0.12.2``` lead to errors because of mismatches with respect to dictionary keys. Anyway, we provide a script (```local/create_xlsr_new.py```) which removes some dictionary keys and stores a new version of the model preventing those errors** (see also [ISSUE](https://github.com/facebookresearch/fairseq/issues/3741)).