satheeshkola-532

{"message": "no candidates in the response: sdk_http_response=HttpResponse(\n headers=\n) candidates=[Candidate(\n finish_reason=,\n index=0\n)] create_time=None response_id=None model_version='gemini-2.5-flash' prompt_feedback=None usage_metadata=GenerateContentResponseUsageMetadata(\n cache_tokens_details=[\n ModalityTokenCount(\n modality=,\n token_count=8525\n ),\n ],\n cached_content_token_count=8525,\n candidates_token_count=89,\n prompt_token_count=8631,\n prompt_tokens_details=[\n ModalityTokenCount(\n modality=,\n token_count=8631\n ),\n...

> `"level": "WARNING"` > > ``` > if ( > not response.candidates > or not response.candidates[0].content > or not response.candidates[0].content.parts > ): > logger.warning(f"no candidates in the response: {response}") >...

> Please try lowering the transformers version, e.g. 4.44. thank you, that error resolved but i am facing another issue which is that it's giving blank response as show in...

> > Please try lowering the transformers version, e.g. 4.44. > > thank you, that error resolved but i am facing another issue which is that it's giving blank response...

@Jintao-Huang > fixed thank you @Jintao-Huang , it is generating text responses only on giving audio input but not both the text response and audio output ? Actually llama omni...

> > [@satheeshkola-532](https://github.com/satheeshkola-532) did you get any luck with mini-omni? > > I'm Author Zhifei. Do you want it? > Yes please

hi @shihuai , could you please share the training scripts.. it would be very helpful for us to reproduce the model for indian languages? my mail id: [email protected]