Update WhisperPlus version and fix example URL

README.md

@@ -20,6 +20,10 @@
 pip install whisperplus
 ```
 
+# 🤗 Model Hub
+
+You can find the models on the [HuggingFace Spaces](https://huggingface.co/spaces/ArtGAN/WhisperPlus) or on the [HuggingFace Model Hub](https://huggingface.co/models?search=whisper)
+
 ## 🎙️ Usage
 
 To use the whisperplus library, follow the steps below for different tasks:
@@ -29,12 +33,42 @@ To use the whisperplus library, follow the steps below for different tasks:
 ```python
 from whisperplus import SpeechToTextPipeline, download_and_convert_to_mp3
 
-url = "https://www.youtube.com/watch?v=6Dh-RL__uN4"
+url = "https://www.youtube.com/watch?v=di3rHkEZuUw"
 video_path = download_and_convert_to_mp3(url)
-pipeline = SpeechToTextPipeline()
+pipeline = SpeechToTextPipeline(model_id="openai/whisper-large-v3")
 transcript = pipeline(
-    audio_path=video_path, model_id="openai/whisper-large-v3", language="turkish"
+    audio_path=video_path, model_id="openai/whisper-large-v3", language="english
 )
 
 return transcript
 ```
+
+### Contri
+
+```bash
+pip install -r dev-requirements.txt
+pre-commit install
+pre-commit run --all-files
+```
+
+## 📜 License
+
+This project is licensed under the terms of the Apache License 2.0.
+
+## 🤗 Acknowledgments
+
+This project is based on the [HuggingFace Transformers](https://github.com/huggingface/transformers) library.
+
+## 🤗 Citation
+
+```bibtex
+@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}
+}
+```

whisperplus/__init__.py

@@ -1,7 +1,7 @@
 from whisperplus.pipelines.whisper import SpeechToTextPipeline
 from whisperplus.utils.download_utils import download_and_convert_to_mp3
 
-__version__ = '0.0.3'
+__version__ = '0.0.4'
 __author__ = 'kadirnar'
 __license__ = 'Apache License 2.0'
 __all__ = ['']

whisperplus/app.py

@@ -5,6 +5,19 @@
 
 
 def main(url, model_id, language_choice):
+    """
+    Main function that downloads and converts a video to MP3 format, performs speech-to-text conversion using
+    a specified model, and returns the transcript along with the video path.
+
+    Args:
+        url (str): The URL of the video to download and convert.
+        model_id (str): The ID of the speech-to-text model to use.
+        language_choice (str): The language choice for the speech-to-text conversion.
+
+    Returns:
+        transcript (str): The transcript of the speech-to-text conversion.
+        video_path (str): The path of the downloaded video.
+    """
     video_path = download_and_convert_to_mp3(url)
     pipeline = SpeechToTextPipeline(model_id)
     transcript = pipeline(audio_path=video_path, model_id=model_id, language=language_choice)
@@ -61,7 +74,7 @@ def app():
         gr.Examples(
             examples=[
                 [
-                    "https://www.youtube.com/watch?v=HDX8BE2Pje8",
+                    "https://www.youtube.com/watch?v=di3rHkEZuUw",
                     "openai/whisper-large-v3",
                     "English",
                 ],