-
As of now, it has a not-so-bad type of speech recognition that needs to be improved at the latest. As it would drastically impact any further development and testing in the project
-
Ran into an issue on: 04c3a82 (not present in f905534, so recently introduced)
```
(venv) ➜ tstbtc git:(main) tstbtc transcribe "PATH" --deepgram --diarize --loc lightning-specification -t 'Lig…
-
## What is the current behavior?
When the punctuation characters are spoken after the brief pause, deepgram doesn't return any results back. Eg.:
If I state...
"The patient presents today complai…
-
Settings:
* `interrupt_min_words` set to 2
* Silero VAD + Deepgram STT + Eleven Labs TTS + OpenAI LLM
* All other VoiceAssistant settings use their default values
Steps to repro:
* Begin speaki…
-
### Feature Description
I need to integrate speech-to-text into my own projects along with other AI models and I look forward to Deepgram, an affordable solution, being supported by Vercel AI for sea…
-
I am trying to run the assistant with the new package livekit-agents 0.8.0.dev3, but I am encountering the following error after executing the command python minimal.py start:
```
Traceback (most …
-
We are encountering a very weird bug where sometimes in conversation, VAD/Agent cannot detect end of speech.. the usual flow is that user starts speaking and we can get live transcripts for it but whe…
-
## What is the current behavior?
When deserializing the transcription, it misses the `speaker` and `num_words` properties on the paragraph level. This bug was raised by a user in github discussions…
-
**Is your feature request related to a problem? Please describe.**
I'm always frustrated when I speak Chinese with some English words.
For now, only accept language in recording settings. This may m…
iamsk updated
3 months ago
-
Hello Thibault,
I successfully got your Deepgram package to send and process a .wav file. It works great. It's very easy and useful.
However, I'm trying to work with a stream but haven't had any…