README.md

metadata

title: APi English
emoji: 🏢
colorFrom: pink
colorTo: green
sdk: docker
python_version: '3.12'
app_file: app/main.py
app_port: 7860
short_description: English learning API
models:
  - Qwen/Qwen2.5-0.5B-Instruct
  - openai/whisper-small.en
  - facebook/mms-tts-eng
  - allegro/BiDi-eng-pol
tags:
  - nlp
  - tts
  - asr
  - translation
license: mit
pinned: false

🏢 APi English

APi English is a FastAPI-based API to help learners improve their English using NLP, Text-to-Speech, Automatic Speech Recognition, and Translation.

---

🚀 Features

• NLP Chat: Emma, your friendly English teacher, provides natural replies, grammar corrections, and vocabulary tips.
• Text-to-Speech (TTS): Converts text responses to audio (WAV format).
• Automatic Speech Recognition (ASR): Transcribes user audio into text.
• Translation: Translate between English and Polish.

---

🤖 Models and Licenses

This project uses several open-source AI models from Hugging Face.
Each model retains its original license as listed below:

🔊 Speech Recognition

• Whisper Small (English)
  Licensed under the Apache License 2.0.
  Developed by OpenAI

🗣️ Text-to-Speech (TTS)

• facebook/mms-tts-eng
  Licensed under Creative Commons Attribution Non Commercial 4.0 (CC BY-NC 4.0).
  Developed by AI at Meta.

💬 Natural Language Processing (Chat & Grammar)

• Qwen/Qwen2.5-0.5B-Instruct
  Licensed under Apache License 2.0.
  Developed by Qwen Team

🌐 Translation

• Allegro/BiDi-eng-pol
  Licensed under Creative Commons Attribution 4.0 International (CC BY 4.0).
  Developed by Allegro ML Research

---

⚖️ License Notice

This project integrates open-source models and fully complies with their respective licenses.
All rights to the models belong to their original creators.
The source code of this application is distributed separately under the license defined in this repository.

---

📚 References

1. Whisper Small (English) — OpenAI

@misc{radford2022whisper, doi = {10.48550/ARXIV.2212.04356}, url = {https://arxiv.org/abs/2212.04356}, author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya}, title = {Robust Speech Recognition via Large-Scale Weak Supervision}, publisher = {arXiv}, year = {2022}, copyright = {arXiv.org perpetual, non-exclusive license} }

2. facebook/mms-tts-eng -- AI at Meta

@article{pratap2023mms, title={Scaling Speech Technology to 1,000+ Languages}, author={Vineel Pratap and Andros Tjandra and Bowen Shi and Paden Tomasello and Arun Babu and Sayani Kundu and Ali Elkahky and Zhaoheng Ni and Apoorv Vyas and Maryam Fazel-Zarandi and Alexei Baevski and Yossi Adi and Xiaohui Zhang and Wei-Ning Hsu and Alexis Conneau and Michael Auli}, journal={arXiv}, year={2023} }

3. Qwen/Qwen2.5-0.5B-Instruct — Qwen Team

@misc{qwen2.5, title = {Qwen2.5: A Party of Foundation Models}, url = {https://qwenlm.github.io/blog/qwen2.5/}, author = {Qwen Team}, month = {September}, year = {2024} }

@article{qwen2, title={Qwen2 Technical Report}, author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan}, journal={arXiv preprint arXiv:2407.10671}, year={2024} }

4. Allegro/BiDi-eng-pol — Allegro ML Research

Authors:

• MLR @ Allegro: Artur Kot, Mikołaj Koszowski, Wojciech Chojnowski, Mieszko Rutkowski
• Laniqo.com: Artur Nowakowski, Kamil Guttmann, Mikołaj Pokrywka

🙏 Attributions

This project would not be possible without the amazing work of the open-source community.
Special thanks to the teams and organizations that created and maintain the following models and tools:

• OpenAI for Whisper Small (English) — Licensed under Apache License 2.0.
• Facebook AI Research (FAIR) for facebook/mms-tts-eng — Licensed under Creative Commons Attribution Non Commercial 4.0 (CC BY-NC 4.0).
• Qwen Team for Qwen/Qwen2.5-0.5B-Instruct — Licensed under Apache License 2.0.
• Allegro ML Research for BiDi-eng-pol — Licensed under Creative Commons Attribution 4.0 International (CC BY 4.0).

This application uses these models for educational and research purposes only, in full compliance with their respective licenses.
All rights, trademarks, and credits belong to their original creators.