!PyPI - License !PyPI - Python Version

[[Paper]](https://arxiv.org/pdf/1909.05424.pdf) [[Documentation]](https://facebookresearch.github.io/vizseq) [[Blog]](https://ai.facebook.com/blog/vizseq-a-visual-analysis-toolkit-for-accelerating-text-generation-research)

Task Coverage

| Source | Example Tasks | | :--- | :--- | | Text | Machine translation, text summarization, dialog generation, grammatical error correction, open-domain question answering | | Image | Image captioning, image question answering, optical character recognition | | Audio | Speech recognition, speech translation | | Video | Video description | | Multimodal | Multimodal machine translation

Metric Coverage

| Type | Metrics | | :--- | :--- | | N-gram-based | BLEU (Papineni et al., 2002), NIST (Doddington, 2002), METEOR (Banerjee et al., 2005), TER (Snover et al., 2006), RIBES (Isozaki et al., 2010), chrF (Popović et al., 2015), GLEU (Wu et al., 2016), ROUGE (Lin, 2004), CIDEr (Vedantam et al., 2015), WER | | Embedding-based | LASER (Artetxe and Schwenk, 2018), BERTScore (Zhang et al., 2019) |

Getting Started

Installation

You can install VizSeq from PyPI repository:

$ pip install vizseq

Or install it from source:

$ git clone https://github.com/facebookresearch/vizseq
$ cd vizseq
$ pip install -e .

The base install keeps dependencies lightweight. Install optional extras only if you need them:

$ pip install vizseq[embeddings]  # BERTScore scorer (pulls in torch, modern torch 2.x supported)
$ pip install vizseq[laser]       # legacy LASER scorer (pins torch<2.0, numpy<2.0)
$ pip install vizseq[audio]       # reading .wav/.flac/.sph audio sources
$ pip install vizseq[translate]   # Google Translate integration
$ pip install vizseq[all]         # everything above (embeddings, audio, translate)

Documentation

Jupyter Notebook Examples

• Basic example
• Multimodal Machine Translation
• Multilingual Machine Translation
• Speech Translation

Fairseq integration

Web App Example

$ git clone https://github.com/facebookresearch/vizseq
$ cd vizseq
$ python get_example_data.py

$ vizseq-server --port 9001 --data-root ./examples/data

http://localhost:9001

License

Citation

@inproceedings{wang2019vizseq,
  title = {VizSeq: A Visual Analysis Toolkit for Text Generation Tasks},
  author = {Changhan Wang, Anirudh Jain, Danlu Chen, Jiatao Gu},
  booktitle = {In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing: System Demonstrations},
  year = {2019},
}

Contact