Grayscale/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(asr): add StepFun ASR SSE transcription provider

Browse Source 
- Add StepFunTranscriptionProvider class in nanobot/providers/transcription.py
- New _post_stepfun_asr_with_retry() function handling SSE stream parsing
  (transcript.text.delta → transcript.text.done event sequence)
- Register 'stepfun' in transcription_registry.py with default model stepaudio-2.5-asr
- Reuse existing stepfun provider config (apiBase can point to Plan endpoint)
- Add 17 tests covering SSE parsing, retry contract, empty-text edge case, and registry integration
- Update docs/configuration.md with stepfun ASR documentation

StepFun ASR uses a dedicated SSE endpoint (/v1/audio/asr/sse) rather
than the chat-completions or Whisper multipart formats used by other
providers. Users on Step Plan can set apiBase to the Plan endpoint.
This commit is contained in:
moran
2026-06-10 15:50:38 +08:00
committed by Xubin Ren
parent 31bfec58d0
commit 7930058348
5 changed files with 582 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/configuration.md
+3 -3
View File
@@ -239,7 +239,7 @@ Tracing covers the providers that go through nanobot's OpenAI-compatible client
| `lm_studio` | LLM (local, LM Studio) | — |
| `atomic_chat` | LLM (local, [Atomic Chat](https://atomic.chat/)) | — |
| `mistral` | LLM | [docs.mistral.ai](https://docs.mistral.ai/) |
| `stepfun` | LLM (Step Fun/阶跃星辰) | [platform.stepfun.com](https://platform.stepfun.com) |
| `stepfun` | LLM (Step Fun/阶跃星辰) + Voice transcription (ASR) | [platform.stepfun.com](https://platform.stepfun.com) |
| `ovms` | LLM (local, OpenVINO Model Server) | [docs.openvino.ai](https://docs.openvino.ai/2026/model-server/ovms_docs_llm_quickstart.html) |
| `vllm` | LLM (local, any OpenAI-compatible server) | — |
| `nvidia` | LLM (NVIDIA NIM) | [build.nvidia.com](https://build.nvidia.com/) |
@@ -1294,8 +1294,8 @@ Configure transcription under the top-level `transcription` section:
| Setting | Default | Description |
|---------|---------|-------------|
| `enabled` | `true` | Enables audio transcription for both chat-channel voice messages and WebUI/desktop microphone input. |
| `provider` | `"groq"` | Transcription backend: `"groq"`, `"openai"`, `"openrouter"`, `"xiaomi_mimo"`, or `"assemblyai"`. |
| `model` | provider default | Optional transcription model override. Defaults to `whisper-large-v3` for Groq, `whisper-1` for OpenAI, `openai/whisper-1` for OpenRouter, `mimo-v2.5-asr` for Xiaomi MiMo ASR, and `universal-3-pro,universal-2` for AssemblyAI. OpenRouter accepts only speech-to-text models on its transcription endpoint, such as `nvidia/parakeet-tdt-0.6b-v3`, `openai/whisper-1`, or `openai/gpt-4o-transcribe`; chat LLMs are rejected there. AssemblyAI accepts a comma-separated model fallback list. |
| `provider` | `"groq"` | Transcription backend: `"groq"`, `"openai"`, `"openrouter"`, `"xiaomi_mimo"`, `"stepfun"`, or `"assemblyai"`. |
| `model` | provider default | Optional transcription model override. Defaults to `whisper-large-v3` for Groq, `whisper-1` for OpenAI, `openai/whisper-1` for OpenRouter, `mimo-v2.5-asr` for Xiaomi MiMo ASR, `stepaudio-2.5-asr` for StepFun ASR, and `universal-3-pro,universal-2` for AssemblyAI. OpenRouter accepts only speech-to-text models on its transcription endpoint, such as `nvidia/parakeet-tdt-0.6b-v3`, `openai/whisper-1`, or `openai/gpt-4o-transcribe`; chat LLMs are rejected there. AssemblyAI accepts a comma-separated model fallback list. |
| `language` | `null` | Optional ISO-639 language hint, e.g. `"en"`, `"zh"`, `"ko"`, or `"ja"`. |
| `maxDurationSec` | `120` | Maximum WebUI/desktop recording duration. |
| `maxUploadMb` | `25` | Maximum WebUI/desktop audio upload size. |