-
Whisper may hallucinate text when an audio chunk is silence or noise (see https://github.com/elixir-nx/bumblebee/issues/377#issuecomment-2208521942). The openai-whisper implementation has `no_speech_t…
-
- [ ] Train or download a KWS model for your hexapod's onboard computer.
- [ ] Respond to keywords using pre-programmed responses or integrate with an AI like ChatGPT for dynamic conversation.
- […
-
A system to assist physically impaired individuals by translating Indian Sign Language (ISL) into text or speech, enabling better communication. The proposed solution is to build a real-time detection…
-
# Task Name
Hate speech detection
## Task Objective
Hate speech is considered one of the pivotal challenges afflicting online social media today. This task aims to classify speech into "hate"…
-
# Speech Emotion Diarization
Speech Emotion Change Detection system can accurately identify shifts in emotion within a single input utterance. The input is an utterance, and the prediction is a ser…
-
Hi,
Im having problems running the program:
`Sending session update: {"type": "session.update", "session": {"turn_detection": {"type": "server_vad"}, "input_audio_format": "g711_ulaw", "output_…
-
Hey man! Great job with the library, been super duper helpful.
I've been running some tests with live speech, which will be my use case, and I've seen that oftentimes when the audio gets normalized…
-
From the README:
```
...
// [Default: false] Continuous recognition.
// If false:
// - on iOS 17-, recognition will run until no speech is detected for 3 seconds.
// - on iOS 18+ and…
-
In VAD mode it seems you cannot interrupt the assistant. It makes a short break, but then keeps on going.
-
I noticed in the `whisper.h` file that the `no_speech_thold` is commented as not implemented, I've seen this in the python version from OpenAI and found it to be very useful, or at least getting out t…