# Bengali.AI Speech Recognition — Data

来源：https://www.kaggle.com/competitions/bengaliai-speech/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The competition dataset comprises about 1200 hours of recordings of Bengali speech. Your goal is to transcribe recordings of speech that is *out-of-distribution* with respect to the training set.

Note that this is a [**Code Competition**](https://www.kaggle.com/competitions/bengaliai-speech/overview/code-requirements), in which the actual test set is hidden. In this public version, we give some sample data in the correct format to help you author your solutions. The full test set contains about 20 hours of speech in almost 8000 MP3 audio files. All of the files in the test set are encoded at a sample rate of 32k, a bit rate of 48k, in one channel. The test set annotations were normalized with the [bnUnicodeNormalizer](https://pypi.org/project/bnunicodenormalizer/).

Details on the dataset are available in the dataset paper: https://arxiv.org/abs/2305.09688

Citation:
```json
@article{rakib2023oodspeech,
  title={{OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking},
  author={Rakib, Fazle Rabbi and Dip, Souhardya Saha and Alam, Samiul and Tasnim, Nazia and Shihab, Md Istiak Hossain and Ansary, Md Nazmuddoha and Hossen, Syed Mobassir and Meghla, Marsia Haque and Mamun, Mamunur and Sadeque, Farig and others},
  journal={Proc. Interspeech 2023},
  year={2023}
}
```



## Files and Field Descriptions ##

- **train/** The training set, comprising several thousand recordings in MP3 format.
- **test/** The test set, comprising spontaneous speech recordings from eighteen domains, seventeen of which are out-of-distribution with respect to the training set. There may be domains in the private test set that are not in the public test set.
- **examples/** An example recording for each test set domain. You may find these example recordings helpful for creating models robust to domain variation. These are representative recordings and none of them are present in the test set.
- **train.csv** Sentence labels for the training set.
  - `id` A unique identifier for this instance. Corresponds to the file `{id}.mp3` in **train/**.
  - `sentence` A plain-text transcription of the recording. Your goal is to predict these sentences for each recording in the test set.
  - `split` Whether `train` or `valid`. The annotations in the `valid` split have been manually reviewed and corrected, while the annotations in the `train` split have only been algorithmically cleaned. The `valid` samples will generally have higher quality annotations than the `train` samples, but are otherwise drawn from the same distribution.
- **sample_submission.csv** A sample submission file in the correct format. See the [**Evaluation**](https://www.kaggle.com/competitions/bengaliai-speech/overview/evaluation) page for more details.