bit

KO | EN

gitlite — search

#python #golang #animation #ai-agents #tensorflow #dotnet #ios #openai #ai-agent #awesome-list

(★ 9)

A cross-species neural foundation model for end-to-end speech decoding

파일 탐색기

ZIP 다운로드

- trainer.yaml
- - prepare_data.py
  - README.md
- - prepare_data.py
  - README.md
- zero2-bf16.yaml
- zero3-bf16.yaml
- bci.py
- data_augmentation.py
- model_output.py
- model_utils.py
- ndt.py
- trainer.py
- config.py
- datasets.py
- eval_llm.py
- eval_phoneme.py
- eval_spike.py
- utils.py
env.yaml
eval_llm.py
eval_phoneme.py
LICENSE
README.md
registry.py
train.py
vocab.json

# CDN으로 사용하기

jsDelivr

jsDelivr는 공개 GitHub 리포지토리를 별도 설정 없이 CDN으로 즉시 서빙합니다. 버전과 파일을 고르면 웹페이지에 바로 붙일 수 있는 링크와 예시 코드가 만들어집니다.

버전

파일

링크

예시

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

## BraIn-to-Text (BIT)

**B**ra**I**n-to-**T**ext (**BIT**) is an end-to-end speech BCI framework that connects a transformer-based neural encoder with audio LLMs to directly generate sentences from neural activity.

- [Paper](https://arxiv.org/abs/2511.21740)
- [Setup](#environment-setup)
- [Training](#training)
- [Evaluation](#eval)

## Setup

```bash
conda env create -f env.yaml
```

#### Brain2Text 25

Download data from [DRYAD](https://datadryad.org/dataset/doi:10.5061/dryad.dncjsxm85) and rename it to `brandman_2024_text`.

#### Brain2Text 24

Download `competitionData.tar.gz` from [DRYAD](https://datadryad.org/dataset/doi:10.5061/dryad.x69p8czpq) and rename it to `willett_2023_text`.

## Training

Update trainer YAML to use your own data and checkpoint path. For example, change the following entries in `configs/finetune/phoneme/ndt/trainer.yaml`:

```yaml
dirs:
  data_dir: YOUR_DATA_DIR
  checkpoint_dir: YOUR_CHECKPOINT_DIR
  log_dir: YOUR_LOG_DIR
```

Run the following command to train a model:

```bash
python train.py --training_mode MODE \
 --dataset DATASET \
 --features FEATURES \
 --encoder ENCODER \
 --task TASK \
 [--ft_ckpt CKPT] \
 [--ds_config DS_CONFIG] \
 [--kwargs KEY=VALUE ...]
```

- *--training_mode: train_from_scratch, finetune*
- *--encoder: ndt*
- *--task: phoneme, sentence*
- *--dataset: willett_2023_text, brandman_2024_text*
- *--features: all, tx1, spikePow*
- *--ft_ckpt: path to finetuned model checkpoint (optional)*

#### Example

1. Train from scratch for phoneme decoding:

```bash
python train.py --training_mode train_from_scratch \
                --dataset brandman_2024_text \
                --features all \
                --encoder ndt \
                --task phoneme
```

2. Fine-tune the above model for sentence decoding:

```bash
python train.py --training_mode finetune \
                --dataset brandman_2024_text \
                --features all \
                --encoder ndt \
                --task sentence \
                --ft_ckpt YOUR_MODEL_PATH
```

## Evaluation

Once you have the fine-tuned model, you can generate sentence predictions in two stages:

1. Run the following command to predict phonemes:

```bash
python eval_phoneme.py --model_path YOUR_MODEL_PATH --eval_split val
```

- *--eval_split: val, test, holdout*
- *"val" corresponds to the benchmark test set; use "holdout" for the holdout set of the competition* 
- *{eval_split}_phoneme_logits.pt is saved for use in language model rescoring*

2. Run the following command to predict sentences using an LLM:

```bash
python eval_llm.py --model_path YOUR_MODEL_PATH --eval_split val
```

- *--nbest: number of candidate sentences for nucleus sampling (optional)*
- *--phoneme_logits_path: path to saved phoneme logits (optional)*

## Citation
Please cite our paper if you use this code in your own work:
```
@inproceedings{zhangcross,
  title={A cross-species neural foundation model for end-to-end speech decoding},
  author={Zhang, Yizi and He, Linyang and Fan, Chaofei and Liu, Tingkai and Yu, Han and Le, Trung and Li, Jingyuan and Linderman, Scott and Duncker, Lea and Willett, Francis R and others},
  booktitle={The Fourteenth International Conference on Learning Representations}
}
```

bit

오너의 다른 레포

파일 탐색기

# CDN으로 사용하기

Was this content helpful?

Recent Feedback

bit

오너의 다른 레포

파일 탐색기

# CDN으로 사용하기

Was this content helpful?

Recent Feedback

Download README