add whisper-asr-webservice

README.md

@@ -429,6 +429,7 @@ A collection of delicious docker recipes.
 - [x] ohmyform
   - [x] api
   - [x] ui
+- [x] onerahmet/openai-whisper-asr-webservice
 - [x] osixia/openldap
 - [x] openresty/openresty
 - [x] opensearchproject/opensearch :bucket:

whisper-asr-webservice/README.md

@@ -0,0 +1,26 @@
+whisper-asr-webservice
+======================
+
+[Whisper ASR Webservice][1] is a free transcription service powered by Whisper AI.
+
+It supports following whisper models:
+
+- [openai/whisper](https://github.com/openai/whisper)
+- [SYSTRAN/faster-whisper](https://github.com/SYSTRAN/faster-whisper)
+
+## Server
+
+```bash
+$ docker compose up -d
+$ curl http://127.0.0.1:9000/docs
+```
+
+## Client
+
+```bash
+$ wget -O audio.wav https://github.com/rhasspy/piper/raw/master/notebooks/wav/en/success.wav
+$ curl -F audio_file=@audio.wav "http://127.0.0.1:9000/asr?task=transcribe&output=srt"
+$ curl -F audio_file=@audio.wav "http://127.0.0.1:9000/detect-language"
+```
+
+[1]: https://github.com/ahmetoner/whisper-asr-webservice

whisper-asr-webservice/docker-compose.yml

@@ -0,0 +1,13 @@
+version: "3.8"
+services:
+  asr:
+    image: onerahmet/openai-whisper-asr-webservice
+    ports:
+      - "9000:9000"
+    volumes:
+      - ./data:/data
+    environment:
+      - ASR_MODEL=medium
+      - ASR_ENGINE=faster_whisper
+      - ASR_MODEL_PATH=/data
+    restart: unless-stopped