Support whisper asr-webservice

README.md

@@ -9,9 +9,10 @@ The pipeline:
 
 1. **acquire** — download audio/video via `yt-dlp` (or use a local video file)
 2. **separate** — split vocals/instrumental with Demucs
-3. **transcribe** — send the vocal stem to your own intranet OpenAI-compatible
-   Whisper server, as a sanity check that the supplied lyrics match the audio
-   and to locate vocal sections
+3. **transcribe** — send the vocal stem to your own intranet Whisper server
+   (OpenAI-compatible, or [onerahmet/openai-whisper-asr-webservice](https://github.com/ahmetoner/whisper-asr-webservice)),
+   as a sanity check that the supplied lyrics match the audio and to locate
+   vocal sections
 4. **align** — forced-align the *supplied* reference lyrics against the vocal
    stem with wav2vec2 (torchaudio's MMS_FA) to get word timings
 5. **pitch** — track pitch on the vocal stem with torchcrepe
@@ -45,8 +46,15 @@ $EDITOR config.toml   # set whisper_url at minimum
 ```
 
 See `config.example.toml` for every available field (`whisper_url`,
-`whisper_api_key`, `whisper_model`, `output_dir`, `work_dir`, `creator`,
-`demucs_model`, `crepe_model`, `device`, `bind_host`, `port`).
+`whisper_api_key`, `whisper_model`, `whisper_api`, `output_dir`, `work_dir`,
+`creator`, `demucs_model`, `crepe_model`, `device`, `bind_host`, `port`).
+
+`whisper_api` selects the wire format: `"openai"` (default) speaks the
+OpenAI-compatible `POST {whisper_url}/audio/transcriptions` API; `"asr-webservice"`
+speaks [onerahmet/openai-whisper-asr-webservice](https://github.com/ahmetoner/whisper-asr-webservice)'s
+`POST {whisper_url}/asr` API instead (point `whisper_url` at that server's base
+URL with no `/v1` suffix — `whisper_model`/`whisper_api_key` are unused for
+this backend, since the model is fixed by how that server was started).
 
 ## Docker
 

config.example.toml

@@ -1,6 +1,8 @@
 whisper_url = "http://whisper.intranet:9000/v1"
 # whisper_api_key = ""
 # whisper_model = "whisper-1"
+# whisper_api = "openai"  # or "asr-webservice" for onerahmet/openai-whisper-asr-webservice
+                          # (set whisper_url without the /v1 suffix, e.g. "http://whisper.intranet:9000")
 output_dir = "/data/output"
 work_dir = "/data/work"
 creator = "brad"

src/karaoke_maker/config.py

@@ -9,6 +9,7 @@ class Config:
     whisper_url: str
     whisper_api_key: str | None = None
     whisper_model: str = "whisper-1"
+    whisper_api: str = "openai"
     output_dir: Path = Path("output")
     work_dir: Path = Path("work")
     creator: str = "karaoke-maker"

src/karaoke_maker/whisper_client.py

@@ -19,18 +19,35 @@ def transcribe(cfg: Config, audio_path: Path, language: str | None = None,
     headers = {}
     if cfg.whisper_api_key:
         headers["Authorization"] = f"Bearer {cfg.whisper_api_key}"
-    data = {"model": cfg.whisper_model, "response_format": "verbose_json"}
+    iso_language = None
     if language:
         entry = LANGUAGES.get(language.lower())
-        data["language"] = entry.iso if entry else language
+        iso_language = entry.iso if entry else language
+
     own = client is None
     client = client or httpx.Client(timeout=600)
     try:
         with audio_path.open("rb") as f:
-            resp = client.post(
-                f"{cfg.whisper_url.rstrip('/')}/audio/transcriptions",
-                headers=headers, data=data,
-                files={"file": (audio_path.name, f, "audio/wav")})
+            if cfg.whisper_api == "asr-webservice":
+                # onerahmet/openai-whisper-asr-webservice: fixed /asr endpoint,
+                # file field is "audio_file", and language/output are query
+                # params rather than form fields - there is no "model" param,
+                # the model is fixed by how that server was started.
+                params = {"output": "json"}
+                if iso_language:
+                    params["language"] = iso_language
+                resp = client.post(
+                    f"{cfg.whisper_url.rstrip('/')}/asr",
+                    headers=headers, params=params,
+                    files={"audio_file": (audio_path.name, f, "audio/wav")})
+            else:
+                data = {"model": cfg.whisper_model, "response_format": "verbose_json"}
+                if iso_language:
+                    data["language"] = iso_language
+                resp = client.post(
+                    f"{cfg.whisper_url.rstrip('/')}/audio/transcriptions",
+                    headers=headers, data=data,
+                    files={"file": (audio_path.name, f, "audio/wav")})
         resp.raise_for_status()
         return [TranscriptSegment(s["start"], s["end"], s["text"].strip())
                 for s in resp.json().get("segments", [])]

tests/test_whisper.py

@@ -36,3 +36,25 @@ def test_transcribe_maps_language_to_iso_code(tmp_path):
     transcribe(cfg, audio, language="Japanese", client=client)
     assert 'name="language"' in seen["body"]
     assert "\r\n\r\nja\r\n" in seen["body"]
+
+
+def test_transcribe_asr_webservice_hits_fixed_asr_endpoint(tmp_path):
+    audio = tmp_path / "v.wav"
+    audio.write_bytes(b"RIFF")
+    seen = {}
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        seen["url"] = str(request.url)
+        seen["body"] = request.read().decode("utf-8", errors="replace")
+        return httpx.Response(200, json={
+            "text": "hello world",
+            "segments": [{"start": 0.5, "end": 2.0, "text": " hello world"}],
+        })
+
+    client = httpx.Client(transport=httpx.MockTransport(handler))
+    cfg = Config(whisper_url="http://w:9000", whisper_api="asr-webservice")
+    segs = transcribe(cfg, audio, language="Japanese", client=client)
+    assert segs == [TranscriptSegment(start=0.5, end=2.0, text="hello world")]
+    assert seen["url"] == "http://w:9000/asr?output=json&language=ja"
+    assert 'name="audio_file"' in seen["body"]
+    assert 'name="model"' not in seen["body"]