michael/AI-Profile-Router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Use qwen3-asr throughout speech integrations

Browse Source
This commit is contained in:
Mikei386
2026-09-25 21:46:43 +02:00
parent 8a323e5b9e
commit da10f6b48d
17 changed files with 52 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files
dev/mock_stt_worker.py
+1 -1
View File
@@ -1,7 +1,7 @@
#!/usr/bin/env python3
"""Mock-STT-Worker für lokale Tests.
Simuliert den Whisper-STT-Worker:
Simuliert den Qwen3-ASR-Adapter:
GET /status → ready: true
POST /transcribe → liefert festes Transkript
dev/test_chunked.py
+8 -8
View File
@@ -220,7 +220,7 @@ def main() -> None:
# Test 1: Multipart + Content-Length (bestehender Pfad)
# ------------------------------------------------------------------
print("Test 1: Multipart + Content-Length")
mp = build_multipart({"model": "whisper-1", "language": "de"},
mp = build_multipart({"model": "qwen3-asr", "language": "de"},
file_data=fake_webm)
status, body = http_request(
"POST", PORTS["router"], "/v1/audio/transcriptions",
@@ -235,7 +235,7 @@ def main() -> None:
# Test 2: Multipart + Transfer-Encoding chunked (einfach)
# ------------------------------------------------------------------
print("Test 2: Multipart + chunked (einfach)")
mp = build_multipart({"model": "whisper-1"}, file_data=fake_webm)
mp = build_multipart({"model": "qwen3-asr"}, file_data=fake_webm)
chunked = build_chunked_body([mp])
raw = (
b"POST /v1/audio/transcriptions HTTP/1.1\r\n"
@@ -254,7 +254,7 @@ def main() -> None:
# Test 3: Mehrere unterschiedlich große Chunks
# ------------------------------------------------------------------
print("Test 3: Mehrere unterschiedlich große Chunks")
mp = build_multipart({"model": "whisper-1"}, file_data=fake_webm)
mp = build_multipart({"model": "qwen3-asr"}, file_data=fake_webm)
# In 5 Chunks aufteilen (unterschiedlich groß)
chunks = []
sizes = [10, 50, 7, 100, 33]
@@ -283,7 +283,7 @@ def main() -> None:
# Test 4: Boundary über Chunk-Grenzen verteilt
# ------------------------------------------------------------------
print("Test 4: Boundary über Chunk-Grenzen verteilt")
mp = build_multipart({"model": "whisper-1"}, file_data=fake_webm)
mp = build_multipart({"model": "qwen3-asr"}, file_data=fake_webm)
# Boundary-String finden und Chunk-Grenze genau dorthin setzen
boundary_str = b"--testboundary123"
idx = mp.find(boundary_str, 10) # zweite Boundary (vor file)
@@ -310,7 +310,7 @@ def main() -> None:
# Test 5: Chunk Extensions
# ------------------------------------------------------------------
print("Test 5: Chunk Extensions")
mp = build_multipart({"model": "whisper-1"}, file_data=fake_webm)
mp = build_multipart({"model": "qwen3-asr"}, file_data=fake_webm)
chunks_ext = [
(mp[:20], "ext1=value1"),
(mp[20:60], None),
@@ -335,7 +335,7 @@ def main() -> None:
# hier explizit mit Trailer)
# ------------------------------------------------------------------
print("Test 6: 0-Chunk mit Trailer")
mp = build_multipart({"model": "whisper-1"}, file_data=fake_webm)
mp = build_multipart({"model": "qwen3-asr"}, file_data=fake_webm)
chunked = build_chunked_body([mp])
# Trailer hinzufügen
chunked_with_trailer = chunked.replace(
@@ -376,7 +376,7 @@ def main() -> None:
print("Test 8: Uploadgrößenlimit")
# MAX_UPLOAD_SIZE = 1 MB, also 2 MB senden
big_data = b"A" * (2 * 1024 * 1024)
mp = build_multipart({"model": "whisper-1"}, file_data=big_data)
mp = build_multipart({"model": "qwen3-asr"}, file_data=big_data)
chunked = build_chunked_body([mp[:1024 * 1024], mp[1024 * 1024:]])
raw = (
b"POST /v1/audio/transcriptions HTTP/1.1\r\n"
@@ -402,7 +402,7 @@ def main() -> None:
+ b"WEBM_OPUS_AUDIO_DATA" * 100)
boundary = "950bd961b24c4a32801e31b128c85e09"
mp = build_multipart(
{"model": "whisper-1", "language": "de"},
{"model": "qwen3-asr", "language": "de"},
file_data=webm_data,
filename="recording.webm",
boundary=boundary,
dev/test_multipart.py
+12 -12
View File
@@ -71,13 +71,13 @@ def test_quoted_boundary():
boundary = "----WebKitFormBoundary7MA4YWxkTrZu0gW"
webm = b"\x1a\x45\xdf\xa3" + b"\x00\x01\x02\x03\xff\xfe\xfd" * 50
body, ct = build(
[("model", "whisper-1", None), ("file", webm, "t.webm")],
[("model", "qwen3-asr", None), ("file", webm, "t.webm")],
boundary, quoted=True,
)
fd, fn, fl = parse_multipart(body, ct)
assert fd == webm, "file_data mismatch"
assert fn == "t.webm", f"filename mismatch: {fn!r}"
assert fl["model"] == "whisper-1", f"model mismatch: {fl!r}"
assert fl["model"] == "qwen3-asr", f"model mismatch: {fl!r}"
print(" quoted boundary: OK")
@@ -109,7 +109,7 @@ def test_openwebui_style():
f"\r\n--{boundary}\r\n"
f'Content-Disposition: form-data; name="model"\r\n'
f"\r\n"
f"whisper-1\r\n"
f"qwen3-asr\r\n"
f"--{boundary}\r\n"
f'Content-Disposition: form-data; name="temperature"\r\n'
f"\r\n"
@@ -119,7 +119,7 @@ def test_openwebui_style():
fd, fn, fl = parse_multipart(body, ct)
assert fd == webm, "file_data mismatch"
assert fn == "rec.webm", f"filename mismatch: {fn!r}"
assert fl["model"] == "whisper-1", f"model mismatch: {fl!r}"
assert fl["model"] == "qwen3-asr", f"model mismatch: {fl!r}"
assert fl["temperature"] == "0.0", f"temperature mismatch: {fl!r}"
print(" Open-WebUI-artig: OK")
@@ -128,13 +128,13 @@ def test_file_before_model():
"""File-Feld vor model-Feld."""
boundary = "boundary123"
body, ct = build(
[("file", b"DATA", "f.wav"), ("model", "whisper-1", None)],
[("file", b"DATA", "f.wav"), ("model", "qwen3-asr", None)],
boundary, quoted=False,
)
fd, fn, fl = parse_multipart(body, ct)
assert fd == b"DATA", "file_data mismatch"
assert fn == "f.wav", f"filename mismatch: {fn!r}"
assert fl["model"] == "whisper-1", f"model mismatch: {fl!r}"
assert fl["model"] == "qwen3-asr", f"model mismatch: {fl!r}"
print(" File vor model: OK")
@@ -142,13 +142,13 @@ def test_file_after_model():
"""model-Feld vor File-Feld."""
boundary = "boundary456"
body, ct = build(
[("model", "whisper-1", None), ("file", b"DATA", "g.wav")],
[("model", "qwen3-asr", None), ("file", b"DATA", "g.wav")],
boundary, quoted=False,
)
fd, fn, fl = parse_multipart(body, ct)
assert fd == b"DATA", "file_data mismatch"
assert fn == "g.wav", f"filename mismatch: {fn!r}"
assert fl["model"] == "whisper-1", f"model mismatch: {fl!r}"
assert fl["model"] == "qwen3-asr", f"model mismatch: {fl!r}"
print(" File nach model: OK")
@@ -182,13 +182,13 @@ def test_extra_headers_ignored():
f"\r\n--{boundary}\r\n"
f'Content-Disposition: form-data; name="model"\r\n'
f"\r\n"
f"whisper-1\r\n"
f"qwen3-asr\r\n"
f"--{boundary}--\r\n"
).encode()
fd, fn, fl = parse_multipart(body, ct)
assert fd == webm, "file_data mismatch"
assert fn == "x.webm", f"filename mismatch: {fn!r}"
assert fl["model"] == "whisper-1", f"model mismatch: {fl!r}"
assert fl["model"] == "qwen3-asr", f"model mismatch: {fl!r}"
print(" Extra-Header ignoriert: OK")
@@ -198,7 +198,7 @@ def test_all_fields():
body, ct = build(
[
("file", b"AUDIO", "a.webm"),
("model", "whisper-1", None),
("model", "qwen3-asr", None),
("language", "de", None),
("prompt", "Kontext", None),
("response_format", "verbose_json", None),
@@ -209,7 +209,7 @@ def test_all_fields():
fd, fn, fl = parse_multipart(body, ct)
assert fd == b"AUDIO", "file_data mismatch"
assert fn == "a.webm", f"filename mismatch: {fn!r}"
assert fl["model"] == "whisper-1", f"model mismatch: {fl!r}"
assert fl["model"] == "qwen3-asr", f"model mismatch: {fl!r}"
assert fl["language"] == "de", f"language mismatch: {fl!r}"
assert fl["prompt"] == "Kontext", f"prompt mismatch: {fl!r}"
assert fl["response_format"] == "verbose_json", f"response_format mismatch: {fl!r}"