Instructions to use openai/whisper-large-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-large-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-large-v3") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-large-v3") - Inference
- Notebooks
- Google Colab
- Kaggle
Add Urdu (Pakistan) language speech to text detection
OpenAI doing great things, Whisper model unmatchable for recognise speech to text, i think Whisper model using in ChatGPT 4o for recognition, i have request, Iโm from Pakistan ๐ต๐ฐ our national language is Urdu, many people think Urdu and Hindi same but itโs not like that, India ๐ฎ๐ณ is the another country, yes in India many people speak Urdu language but those people accent much difference from us, also Hindi letters writing text completely different from us, I have request please add Urdu (Pakistan) language speech detect feature into ChatGPT with reply with Pakistani people accent voice, on internet for Urdu (Pakistan) language two voices available one is Asd male voice and second one is Uzma female voice, both voiced very robotic very irritating, add Urdu (Pakistan) language natural voice and capable to read Urdu (Pakistan) language text, I hope you find mine request thank you.
Is there any other ASR system for Urdu?