> ## Documentation Index > Fetch the complete documentation index at: https://dragonwingdocs.qualcomm.com/llms.txt > Use this file to discover all available pages before exploring further. # 运行 Audio Analytics 容器 > 部署并运行 Audio Analytics 容器,实现设备端 ASR、文本翻译和 TTS。 Qualcomm 的 Audio Analytics 容器通过 REST 和 WebSocket API 对外提供语音识别 (ASR)、 文本翻译 (T2T) 和文本到语音 (TTS) 能力。所有模型完全在 Qualcomm NPU 上以设备端方式 运行。 ## 主要特性 * **一个容器提供三项服务**:ASR、文本到文本翻译和 TTS 通过单一 API 对外提供 * **NPU 加速**:Whisper、OpusMT、MeloTTS 和 PiperTTS 模型全部运行在 Qualcomm NPU 上, 释放 CPU 用于其他任务 * **多语言**:所有三项服务均支持英语、西班牙语和中文;PiperTTS 另可支持德语和意大利语 * **流式支持**:通过 WebSocket 实现实时转写,同时支持基于文件的批量转写 * **OpenAPI / Swagger UI**:交互式 API 文档可在 `http://:8085/docs` 访问 ## 支持的模型 | 服务 | 模型 | 语言 | 采样率 | | --- | --------------------------------------------------- | ---------- | -------- | | ASR | `whisper-small-quantized` | 英语、西班牙语、中文 | 16000 Hz | | 翻译 | `opus-en-es`、`opus-es-en`、`opus-en-zh`、`opus-zh-en` | 英语、西班牙语、中文 | 不适用 | | TTS | `melo-tts-en`、`melo-tts-es`、`melo-tts-zh` | 英语、西班牙语、中文 | 44100 Hz | | TTS | `piper-tts-en`、`piper-tts-de`、`piper-tts-it` | 英语、德语、意大利语 | 22050 Hz | 以上是当前支持的模型。可分别查询 `/transcriptions/models`、`/translations/models` 和 `/tts/models` 以确认运行时实际加载的模型。 ## 部署 以下步骤假定您已完成设备设置([IQ-9075 EVK](https://dragonwingdocs.qualcomm.com/Ubuntu/devices/iq9075-evk/set-up-the-device) 或 [IQ-8275 EVK](https://dragonwingdocs.qualcomm.com/Ubuntu/devices/iq8275-evk/set-up-the-device))。 完成设备设置后,请按照以下步骤部署并运行 Audio Analytics 容器。 通过 SSH 连接到设备并安装所需软件包: ```bash theme={null} sudo apt update sudo apt install curl unzip docker-compose ``` ```bash theme={null} # Configure Docker group sudo groupadd docker sudo usermod -aG docker $USER newgrp docker ``` 创建模型目录结构,并从 QAI Hub 下载所有模型。 ```bash theme={null} mkdir -p ~/models/audio/asr ~/models/audio/tts ~/models/audio/translation cd ~/models # ASR — Whisper Small curl -L -o whisper_small_quantized.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.57.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcs9075.zip unzip -q whisper_small_quantized.zip -d audio/asr && rm whisper_small_quantized.zip # TTS — MeloTTS (English, Spanish, Chinese) curl -L -o melotts_en.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/melotts_en/releases/v0.57.0/melotts_en-voice_ai-mixed_with_float-qualcomm_qcs9075.zip unzip -q melotts_en.zip -d audio/tts && rm melotts_en.zip curl -L -o melotts_es.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/melotts_es/releases/v0.57.0/melotts_es-voice_ai-mixed_with_float-qualcomm_qcs9075.zip unzip -q melotts_es.zip -d audio/tts && rm melotts_es.zip curl -L -o melotts_zh.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/melotts_zh/releases/v0.57.0/melotts_zh-voice_ai-mixed_with_float-qualcomm_qcs9075.zip unzip -q melotts_zh.zip -d audio/tts && rm melotts_zh.zip # TTS — PiperTTS (English, German, Italian) curl -L -o pipertts_en.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pipertts_en/releases/v0.57.0/pipertts_en-voice_ai-float-qualcomm_qcs9075.zip unzip -q pipertts_en.zip -d audio/tts && rm pipertts_en.zip curl -L -o pipertts_de.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pipertts_de/releases/v0.57.0/pipertts_de-voice_ai-float-qualcomm_qcs9075.zip unzip -q pipertts_de.zip -d audio/tts && rm pipertts_de.zip curl -L -o pipertts_it.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pipertts_it/releases/v0.57.0/pipertts_it-voice_ai-float-qualcomm_qcs9075.zip unzip -q pipertts_it.zip -d audio/tts && rm pipertts_it.zip # Translation — Opus (English ↔ Spanish, English ↔ Chinese) curl -L -o opus_mt_en_es.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/opus_mt_en_es/releases/v0.57.0/opus_mt_en_es-voice_ai-float-qualcomm_qcs9075.zip unzip -q opus_mt_en_es.zip -d audio/translation && rm opus_mt_en_es.zip curl -L -o opus_mt_es_en.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/opus_mt_es_en/releases/v0.57.0/opus_mt_es_en-voice_ai-float-qualcomm_qcs9075.zip unzip -q opus_mt_es_en.zip -d audio/translation && rm opus_mt_es_en.zip curl -L -o opus_mt_en_zh.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/opus_mt_en_zh/releases/v0.57.0/opus_mt_en_zh-voice_ai-float-qualcomm_qcs9075.zip unzip -q opus_mt_en_zh.zip -d audio/translation && rm opus_mt_en_zh.zip curl -L -o opus_mt_zh_en.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/opus_mt_zh_en/releases/v0.57.0/opus_mt_zh_en-voice_ai-float-qualcomm_qcs9075.zip unzip -q opus_mt_zh_en.zip -d audio/translation && rm opus_mt_zh_en.zip ``` ```bash theme={null} mkdir -p ~/models/audio/asr ~/models/audio/tts ~/models/audio/translation cd ~/models # ASR — Whisper Small curl -L -o whisper_small_quantized.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.57.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcs8275.zip unzip -q whisper_small_quantized.zip -d audio/asr && rm whisper_small_quantized.zip # TTS — MeloTTS (English, Spanish, Chinese) curl -L -o melotts_en.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/melotts_en/releases/v0.57.0/melotts_en-voice_ai-mixed_with_float-qualcomm_qcs8275.zip unzip -q melotts_en.zip -d audio/tts && rm melotts_en.zip curl -L -o melotts_es.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/melotts_es/releases/v0.57.0/melotts_es-voice_ai-mixed_with_float-qualcomm_qcs8275.zip unzip -q melotts_es.zip -d audio/tts && rm melotts_es.zip curl -L -o melotts_zh.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/melotts_zh/releases/v0.57.0/melotts_zh-voice_ai-mixed_with_float-qualcomm_qcs8275.zip unzip -q melotts_zh.zip -d audio/tts && rm melotts_zh.zip # TTS — PiperTTS (English, German, Italian) curl -L -o pipertts_en.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pipertts_en/releases/v0.57.0/pipertts_en-voice_ai-float-qualcomm_qcs8275.zip unzip -q pipertts_en.zip -d audio/tts && rm pipertts_en.zip curl -L -o pipertts_de.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pipertts_de/releases/v0.57.0/pipertts_de-voice_ai-float-qualcomm_qcs8275.zip unzip -q pipertts_de.zip -d audio/tts && rm pipertts_de.zip curl -L -o pipertts_it.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pipertts_it/releases/v0.57.0/pipertts_it-voice_ai-float-qualcomm_qcs8275.zip unzip -q pipertts_it.zip -d audio/tts && rm pipertts_it.zip # Translation — Opus (English ↔ Spanish, English ↔ Chinese) curl -L -o opus_mt_en_es.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/opus_mt_en_es/releases/v0.57.0/opus_mt_en_es-voice_ai-float-qualcomm_qcs8275.zip unzip -q opus_mt_en_es.zip -d audio/translation && rm opus_mt_en_es.zip curl -L -o opus_mt_es_en.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/opus_mt_es_en/releases/v0.57.0/opus_mt_es_en-voice_ai-float-qualcomm_qcs8275.zip unzip -q opus_mt_es_en.zip -d audio/translation && rm opus_mt_es_en.zip curl -L -o opus_mt_en_zh.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/opus_mt_en_zh/releases/v0.57.0/opus_mt_en_zh-voice_ai-float-qualcomm_qcs8275.zip unzip -q opus_mt_en_zh.zip -d audio/translation && rm opus_mt_en_zh.zip curl -L -o opus_mt_zh_en.zip \ https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/opus_mt_zh_en/releases/v0.57.0/opus_mt_zh_en-voice_ai-float-qualcomm_qcs8275.zip unzip -q opus_mt_zh_en.zip -d audio/translation && rm opus_mt_zh_en.zip ``` 您的模型目录现在应类似如下结构: ``` ~/models/audio/ ├── asr/ ← whisper_small_quantized ├── tts/ ← melotts_en, melotts_es, melotts_zh, pipertts_en, pipertts_de, pipertts_it └── translation/ ← opus_mt_en_es, opus_mt_es_en, opus_mt_en_zh, opus_mt_zh_en ``` 从 [CodeLinaro audio-analytics deploy 目录](https://git.codelinaro.org/clo/iot-solutions-microservices/audio-analytics/-/tree/main/deploy) 下载适合您设备的 Docker Compose 文件。 **方案 A —— 直接在设备上下载:** ```bash theme={null} curl -L -o docker-compose-qcs9100.yml \ https://git.codelinaro.org/clo/iot-solutions-microservices/audio-analytics/-/raw/main/deploy/docker-compose-qcs9100.yml ``` **方案 B —— 在本地下载并复制到设备:** ```bash theme={null} scp docker-compose-qcs9100.yml ubuntu@:~/ ``` **方案 A —— 直接在设备上下载:** ```bash theme={null} curl -L -o docker-compose-qcs8300.yml \ https://git.codelinaro.org/clo/iot-solutions-microservices/audio-analytics/-/raw/main/deploy/docker-compose-qcs8300.yml ``` **方案 B —— 在本地下载并复制到设备:** ```bash theme={null} scp docker-compose-qcs8300.yml ubuntu@:~/ ``` 后续步骤均使用 `docker-compose-qcs9100.yml`。如果您使用的是 IQ-8275 EVK,请在每条命令中替换为 `docker-compose-qcs8300.yml`。 打开 Docker Compose 文件,按需调整以下环境变量: * **`MODELS_DIR`**:容器内所有模型的基路径(默认:`/mnt/work/models`) * **`SESSION_TIMEOUT_S`**:ASR 流式会话在空闲多少秒后自动关闭(默认:`30`) * **`LOG_LEVEL`**:`10`=DEBUG,`20`=INFO,`30`=WARNING,`40`=ERROR(默认:`20`) 在 `volumes:` 下: * **模型路径**:默认将主机上的 `~/models/audio` 映射到容器中的 `/mnt/work/models`。 如果您将模型放在其他位置,请更新卷挂载的左侧: ```yaml theme={null} volumes: - ~/models/audio:/mnt/work/models:ro ``` 请确认卷挂载指向您的模型目录,并且该目录可被容器读取。如果模型加载失败,请通过 `ls -la ~/models/audio` 检查目录权限。 如果尚未存在容器镜像,Docker Compose 文件会自动拉取。 ```bash theme={null} docker compose -f docker-compose-qcs9100.yml up -d ``` 确认容器正在运行: ```bash theme={null} docker ps | grep audio-analytics ``` 容器就绪后,检查 health 端点: ```bash theme={null} curl http://localhost:8085/audio-analytics/v1/api/health ``` 预期响应: ```json theme={null} { "status": "ok", "uptime": 12345, "active_sessions": 0, "version": "1.0.0" } ``` 您也可以确认加载了哪些模型: ```bash theme={null} curl http://localhost:8085/audio-analytics/v1/api/transcriptions/models curl http://localhost:8085/audio-analytics/v1/api/translations/models curl http://localhost:8085/audio-analytics/v1/api/tts/models ``` 对三项服务分别进行一次快速冒烟测试。 **ASR —— 转写音频:** ```bash theme={null} curl -X POST http://localhost:8085/audio-analytics/v1/api/transcriptions/create \ -F 'file=@audio.wav' \ -F 'model=whisper-small-quantized' \ -F 'language=en' \ -F 'stream=false' ``` 预期响应: ```json theme={null} { "text": "Your transcribed text here.", "language": "en", "type": "transcript.text.done" } ``` **翻译 —— 翻译文本:** ```bash theme={null} curl -X POST http://localhost:8085/audio-analytics/v1/api/translations/translate \ -H 'Content-Type: application/json' \ -d '{"text": ["Hello world"], "model": "opus-en-es", "source_language": "en", "target_language": "es"}' ``` 预期响应: ```json theme={null} { "translations": [{ "translated_text": "Hola mundo", "source_language": "en", "target_language": "es" }] } ``` **TTS —— 合成语音:** ```bash theme={null} curl -X POST http://localhost:8085/audio-analytics/v1/api/tts/synthesize \ -H 'Content-Type: application/json' \ -d '{"text": "Hello, how are you today?", "model": "melo-tts-en", "language": "en", "sample_rate": 44100}' \ --output speech.pcm ``` 完成后: ```bash theme={null} docker compose -f docker-compose-qcs9100.yml down ``` ## 查看日志 所有容器输出都可通过 `docker logs` 查看,不存在单独的日志文件。 ```bash theme={null} # Stream all logs docker logs audio-analytics -f -t ``` 若要调整日志详细程度,请在 Docker Compose 文件中设置 `LOG_LEVEL` 并重启容器: | 值 | 级别 | | ---- | -------- | | `10` | DEBUG | | `20` | INFO(默认) | | `30` | WARNING | | `40` | ERROR | ## 下一步 基于文件和实时流式的转写 以多种语言合成自然语音 在设备端在不同语言之间进行文本翻译