Open Kanthavel-Spindox opened 1 week ago
After setting up the default up following the tutorial, the speech interaction with the Avatar does not work.
The UI response "Sorry, could you retry?"
In the API, the following logs appear
api-1 | [Nest] 1 - 09/13/2024, 1:16:14 PM LOG [SessionService] Creating session sessionId=9fc53245-35b9-4213-99ab-ad58edc20bec api-1 | [Nest] 1 - 09/13/2024, 1:16:58 PM WARN [LLMProviderService] Failed to fetch model for ollama: Model sermas-llama3 is not available from provider ollama api-1 | [Nest] 1 - 09/13/2024, 1:17:01 PM LOG [SessionAgentService] Received hearthbeat status=ready moduleId=avatar api-1 | [Nest] 1 - 09/13/2024, 1:17:01 PM LOG [SessionService] Creating session sessionId=731c9190-2922-4969-b801-507a2b110594 api-1 | [Nest] 1 - 09/13/2024, 1:17:04 PM WARN [MonitorService] openai time elapsed 1563.912ms api-1 | [Nest] 1 - 09/13/2024, 1:17:20 PM ERROR [SpeechBrainService] Speech classification error: getaddrinfo EAI_AGAIN speechbrain api-1 | [Nest] 1 - 09/13/2024, 1:17:22 PM ERROR [STTProviderService] STT failed: Error: 400 Unrecognized file format. Supported formats: ['flac', 'm4a', 'mp3', 'mp4', 'mpeg', 'mpga', 'oga', 'ogg', 'wav', 'webm'] api-1 | at Function.generate (/app/node_modules/openai/src/error.ts:70:14) api-1 | at OpenAI.makeStatusError (/app/node_modules/openai/src/core.ts:397:21) api-1 | at OpenAI.makeRequest (/app/node_modules/openai/src/core.ts:460:24) api-1 | at processTicksAndRejections (node:internal/process/task_queues:95:5) api-1 | at async OpenAISpeechToText.text (/app/dist/apps/api/main.js:19345:31) api-1 | at async STTProviderService.convertToText (/app/dist/apps/api/main.js:19096:34) api-1 | at async DialogueSpeechService.convertToText (/app/dist/apps/api/main.js:18786:54) api-1 | [Nest] 1 - 09/13/2024, 1:17:32 PM ERROR [SpeechBrainService] Speech classification error: getaddrinfo EAI_AGAIN speechbrain api-1 | [Nest] 1 - 09/13/2024, 1:17:33 PM ERROR [STTProviderService] STT failed: Error: 400 Unrecognized file format. Supported formats: ['flac', 'm4a', 'mp3', 'mp4', 'mpeg', 'mpga', 'oga', 'ogg', 'wav', 'webm'] api-1 | at Function.generate (/app/node_modules/openai/src/error.ts:70:14) api-1 | at OpenAI.makeStatusError (/app/node_modules/openai/src/core.ts:397:21) api-1 | at OpenAI.makeRequest (/app/node_modules/openai/src/core.ts:460:24) api-1 | at processTicksAndRejections (node:internal/process/task_queues:95:5) api-1 | at async OpenAISpeechToText.text (/app/dist/apps/api/main.js:19345:31) api-1 | at async STTProviderService.convertToText (/app/dist/apps/api/main.js:19096:34) api-1 | at async DialogueSpeechService.convertToText (/app/dist/apps/api/main.js:18786:54)
After setting up the default up following the tutorial, the speech interaction with the Avatar does not work.
The UI response "Sorry, could you retry?"
In the API, the following logs appear
api-1 | [Nest] 1 - 09/13/2024, 1:16:14 PM LOG [SessionService] Creating session sessionId=9fc53245-35b9-4213-99ab-ad58edc20bec api-1 | [Nest] 1 - 09/13/2024, 1:16:58 PM WARN [LLMProviderService] Failed to fetch model for ollama: Model sermas-llama3 is not available from provider ollama api-1 | [Nest] 1 - 09/13/2024, 1:17:01 PM LOG [SessionAgentService] Received hearthbeat status=ready moduleId=avatar api-1 | [Nest] 1 - 09/13/2024, 1:17:01 PM LOG [SessionService] Creating session sessionId=731c9190-2922-4969-b801-507a2b110594 api-1 | [Nest] 1 - 09/13/2024, 1:17:04 PM WARN [MonitorService] openai time elapsed 1563.912ms api-1 | [Nest] 1 - 09/13/2024, 1:17:20 PM ERROR [SpeechBrainService] Speech classification error: getaddrinfo EAI_AGAIN speechbrain api-1 | [Nest] 1 - 09/13/2024, 1:17:22 PM ERROR [STTProviderService] STT failed: Error: 400 Unrecognized file format. Supported formats: ['flac', 'm4a', 'mp3', 'mp4', 'mpeg', 'mpga', 'oga', 'ogg', 'wav', 'webm'] api-1 | at Function.generate (/app/node_modules/openai/src/error.ts:70:14) api-1 | at OpenAI.makeStatusError (/app/node_modules/openai/src/core.ts:397:21) api-1 | at OpenAI.makeRequest (/app/node_modules/openai/src/core.ts:460:24) api-1 | at processTicksAndRejections (node:internal/process/task_queues:95:5) api-1 | at async OpenAISpeechToText.text (/app/dist/apps/api/main.js:19345:31) api-1 | at async STTProviderService.convertToText (/app/dist/apps/api/main.js:19096:34) api-1 | at async DialogueSpeechService.convertToText (/app/dist/apps/api/main.js:18786:54) api-1 | [Nest] 1 - 09/13/2024, 1:17:32 PM ERROR [SpeechBrainService] Speech classification error: getaddrinfo EAI_AGAIN speechbrain api-1 | [Nest] 1 - 09/13/2024, 1:17:33 PM ERROR [STTProviderService] STT failed: Error: 400 Unrecognized file format. Supported formats: ['flac', 'm4a', 'mp3', 'mp4', 'mpeg', 'mpga', 'oga', 'ogg', 'wav', 'webm'] api-1 | at Function.generate (/app/node_modules/openai/src/error.ts:70:14) api-1 | at OpenAI.makeStatusError (/app/node_modules/openai/src/core.ts:397:21) api-1 | at OpenAI.makeRequest (/app/node_modules/openai/src/core.ts:460:24) api-1 | at processTicksAndRejections (node:internal/process/task_queues:95:5) api-1 | at async OpenAISpeechToText.text (/app/dist/apps/api/main.js:19345:31) api-1 | at async STTProviderService.convertToText (/app/dist/apps/api/main.js:19096:34) api-1 | at async DialogueSpeechService.convertToText (/app/dist/apps/api/main.js:18786:54)