I am a user of c transformers, and I would like to request a feature to add support for the whisper speech-to-text model. Whisper is a state-of-the-art model that can transcribe speech with high accuracy and low latency, even in noisy environments. It is based on the wav2vec 2.0 framework and trained on a large-scale dataset of diverse speech samples. 🙌
I think adding whisper to the list of supported models would be beneficial for many users who need to process speech data in various domains and scenarios. There is a ggml compatible versions with the huggingface transformers library, and it's available on the huggingface hub: https://huggingface.co/ggerganov/whisper.cpp 🚀
I would appreciate it if you could consider this feature request and let me know if you have any questions or feedback. Thank you for your great work on c transformers and for your attention to this issue. 😊
Yossef-Dawoad
commented
11 months ago
Hello 👋,
I am a user of c transformers, and I would like to request a feature to add support for the whisper speech-to-text model. Whisper is a state-of-the-art model that can transcribe speech with high accuracy and low latency, even in noisy environments. It is based on the wav2vec 2.0 framework and trained on a large-scale dataset of diverse speech samples. 🙌
I think adding whisper to the list of supported models would be beneficial for many users who need to process speech data in various domains and scenarios. There is a ggml compatible versions with the huggingface transformers library, and it's available on the huggingface hub: https://huggingface.co/ggerganov/whisper.cpp 🚀
I would appreciate it if you could consider this feature request and let me know if you have any questions or feedback. Thank you for your great work on c transformers and for your attention to this issue. 😊
Best regards, Yousef Dawoud.