TTS stop before the end
Closed this issue · 6 comments
Hi,
I tried to use june but when it answers the tts doesn't read the full text
PS C:\Users\Rombond\Documents\Perso\AI\june> june-va -v
[system]> LLM model initialized (model_id=llama3:8b-instruct-q4_0; device=cuda)
[system]> No system prompt provided.
[system]> STT model initialized (model_id=openai/whisper-small.en; device=cuda)
[system]> TTS model initialized (model_id=tts_models/en/ljspeech/glow-tts; device=cuda)
[system]> Listening for sound...
[system]> Sound detected, starting recording...
[system]> Silence detected, stopping recording...
[system]> Transcribing audio...
C:\Users\Rombond\AppData\Local\Programs\Python\Python312\Lib\site-packages\transformers\models\whisper\modeling_whisper.py:694: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:455.)
attn_output = torch.nn.functional.scaled_dot_product_attention(
[user]> Sally has three brothers. Each brother has two sisters. How many sisters does Sally have?
[assistant]> A classic lateral thinking puzzle!
Let's break it down:
* Sally has 3 brothers.
* Each of those brothers has 2 sisters.
* Since Sally is one of the sisters, each of her 3 brothers must have Sally as one of their 2 sisters.
So, if each of Sally's 3 brothers has Sally as one of their 2 sisters, that means Sally herself counts as one of her own sisters!
Therefore, Sally has... (drumroll) ...4 sisters: herself and the other 3 sisters who are her brothers' sisters!
I have converted the out.wav into mp4 to upload it here:
https://github.com/user-attachments/assets/c31bd4c2-454a-4410-bbb6-f42a450853b1
This issue is stale because it has been open 15 days with no activity. Remove stale label or comment or this will be closed in 5 days.
still having the issue
Does the prompt work as usual apart from the TTS not working properly? Can you continue having a conversation with the tool, or is the prompt stuck along with the TTS functionality?
Issue still here
Does the prompt work as usual apart from the TTS not working properly? Can you continue having a conversation with the tool, or is the prompt stuck along with the TTS functionality?
It works only one time after that the prompt stuck along with the TTS functionality.
june-va -v
[system]> LLM model initialized (model_id=llama3.1:8b-instruct-q4_0; device=cuda)
[system]> No system prompt provided.
[system]> STT model initialized (model_id=openai/whisper-small.en; device=cuda)
[system]> TTS model initialized (model_id=tts_models/en/ljspeech/glow-tts; device=cuda)
[system]> Listening for sound...
[system]> Sound detected, starting recording...
[system]> Silence detected, stopping recording...
[system]> Transcribing audio...
C:\Users\Rombond\AppData\Local\Programs\Python\Python312\Lib\site-packages\transformers\models\whisper\modeling_whisper.py:694: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:455.)
attn_output = torch.nn.functional.scaled_dot_product_attention(
[user]> Hi, how are you?
[assistant]> I'm just a language model, I don't have feelings or emotions like humans do. However, I'm functioning properly and ready to help with any questions or tasks you may have! How about you? How's your day going so far?
TTS stops after "like humans do" and program stop working