docs(readme): add Faster Whisper usage and base model attribution

README.md

@@ -10,7 +10,7 @@ app_port: 7860
 short_description: "English learning API"
 models:
   - Qwen/Qwen2.5-1.5B-Instruct 
-  - openai/whisper-small.en
+  - faster_whisper/faster-whisper-small-en
   - facebook/mms-tts-eng
   - allegro/BiDi-eng-pol
 tags:
@@ -43,9 +43,12 @@ 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)**](https://huggingface.co/openai/whisper-small.en)  
-  Licensed under the [Apache License 2.0](http://www.apache.org/licenses/LICENSE-2.0).  
-  Developed by [**OpenAI**](https://openai.com/)
+- **Faster Whisper Small (English)**  
+  Efficient CPU/GPU implementation of OpenAI Whisper Small.  
+  Base model: **openai/whisper-small.en**  
+  Licensed under [mit](https://choosealicense.com/licenses/mit/).  
+  Implementation by [**Faster Whisper**](https://huggingface.co/Systran/faster-whisper-small.en)
+
 
 ### 🗣️ Text-to-Speech (TTS)
 - [**facebook/mms-tts-eng**](https://huggingface.co/facebook/mms-tts-eng)  
@@ -74,15 +77,14 @@ The source code of this application is distributed separately under the license
 
 ## 📚 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}
+### 1. Faster Whisper Small (English) — Systran
+@misc{faster_whisper_small,
+  title = {Faster Whisper Small English},
+  author = {Systran AI},
+  note = {CTranslate2-converted version of [**OpenAI Whisper Small**](https://huggingface.co/openai/whisper-small.en) for fast inference with faster_whisper},
+  url = {https://huggingface.co/Systran/faster-whisper-small.en},
+  year = {2024},
+  license = {MIT (conversion), original model Apache 2.0}
 }
 
 ### 2. facebook/mms-tts-eng -- AI at Meta
@@ -123,6 +125,8 @@ This project would not be possible without the amazing work of the open-source c
 Special thanks to the teams and organizations that created and maintain the following models and tools:
 
 - **[OpenAI](https://openai.com/)** for [**Whisper Small (English)**](https://huggingface.co/openai/whisper-small.en) — Licensed under [Apache License 2.0](http://www.apache.org/licenses/LICENSE-2.0).  
+- **[Systran / Faster Whisper](https://huggingface.co/Systran/faster-whisper-small.en)** for [**Faster Whisper Small (English)**](https://huggingface.co/openai/whisper-small.en) — a CTranslate2-converted version of **OpenAI Whisper Small**, optimized for fast CPU/GPU inference.  
+Licensed under [MIT](https://choosealicense.com/licenses/mit/) and Apache 2.0 (original model)
 - **[Facebook AI Research (FAIR)](https://ai.facebook.com/)** for [**facebook/mms-tts-eng**](https://huggingface.co/facebook/mms-tts-eng) — Licensed under [Creative Commons Attribution Non Commercial 4.0 (CC BY-NC 4.0)](https://creativecommons.org/licenses/by-nc/4.0/).  
 - **[Qwen Team](https://qwen.ai/)** for [**Qwen/Qwen2.5-1.5B-Instruct**](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) — Licensed under [Apache License 2.0](http://www.apache.org/licenses/LICENSE-2.0).  
 - **[Allegro ML Research](https://ml.allegro.tech/)** for [**BiDi-eng-pol**](https://huggingface.co/allegro/BiDi-eng-pol) — Licensed under [Creative Commons Attribution 4.0 International (CC BY 4.0)](https://creativecommons.org/licenses/by/4.0/).