[Qwen3TTS] [TTS] [Feat] Refactor voice cache manager (#2108)

Signed-off-by: JuanPZuluaga <juanz9312@gmal.com> Signed-off-by: yiliu30 <yi4.liu@intel.com> Signed-off-by: gcanlin <canlinguosdu@gmail.com> Signed-off-by: Binh Tang <tangbinhna@gmail.com> Signed-off-by: Binh Tang <binht@netflix.com> Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com> Signed-off-by: Rein Yang <ruiruyang2@gmail.com> Signed-off-by: CHEN <116010019@link.cuhk.edu.cn> Signed-off-by: vraiti <vraiti@redhat.com> Signed-off-by: Songrui625 <songrui625@gmail.com> Signed-off-by: Lidang Jiang <lidangjiang@gmail.com> Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com> Signed-off-by: Alex Brooks <albrooks@redhat.com> Co-authored-by: JuanPZuluaga <juanz9312@gmal.com> Co-authored-by: Yi Liu <yi4.liu@intel.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com> Co-authored-by: Canlin Guo <canlinguosdu@gmail.com> Co-authored-by: Binh Tang <tangbinhna@gmail.com> Co-authored-by: Binh Tang <binht@netflix.com> Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com> Co-authored-by: rein yang <73573651+R2-Y@users.noreply.github.com> Co-authored-by: zhumingjue138 <zhumingjue@huawei.com> Co-authored-by: ChenWenjing <54166744+Shirley125@users.noreply.github.com> Co-authored-by: vraiti <vraiti@redhat.com> Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com> Co-authored-by: Sy03 <1370724210@qq.com> Co-authored-by: chickeyton <ngton2014@gmail.com> Co-authored-by: Jerry Song <46962917+Songrui625@users.noreply.github.com> Co-authored-by: Lidang Jiang <119769478+Lidang-Jiang@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Alex Brooks <albrooks@redhat.com> Co-authored-by: linyueqian <linyueqian@outlook.com> Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
2026-04-03 16:51:58 -04:00
1 parent 0e83ebe1d4
commit f50c5a413f
@@ -233,17 +233,20 @@ def test_app(mocker: MockerFixture):
        uploaded_voices = []
        if hasattr(speech_server, "uploaded_speakers"):
            for voice_name, info in speech_server.uploaded_speakers.items():
-                uploaded_voices.append(
-                    {
-                        "name": info.get("name", voice_name),
-                        "consent": info.get("consent", ""),
-                        "created_at": info.get("created_at", 0),
-                        "file_size": info.get("file_size", 0),
-                        "mime_type": info.get("mime_type", ""),
-                        "embedding_source": info.get("embedding_source", "audio"),
-                        "embedding_dim": info.get("embedding_dim"),
-                    }
-                )
+                voice_entry = {
+                    "name": info.get("name", voice_name),
+                    "consent": info.get("consent", ""),
+                    "created_at": info.get("created_at", 0),
+                    "file_size": info.get("file_size", 0),
+                    "mime_type": info.get("mime_type", ""),
+                    "embedding_source": info.get("embedding_source", "audio"),
+                    "embedding_dim": info.get("embedding_dim"),
+                }
+                if info.get("ref_text"):
+                    voice_entry["ref_text"] = info["ref_text"]
+                if info.get("speaker_description"):
+                    voice_entry["speaker_description"] = info["speaker_description"]
+                uploaded_voices.append(voice_entry)
        return {"voices": speakers, "uploaded_voices": uploaded_voices}

    app.add_api_route("/v1/audio/voices", list_voices, methods=["GET"])
@@ -255,7 +258,8 @@ def test_app(mocker: MockerFixture):
        speaker_embedding: str | None = Form(None),
        consent: str = Form(...),
        name: str = Form(...),
-        ref_text: str = Form(None),
+        ref_text: str | None = Form(None),
+        speaker_description: str | None = Form(None),
    ):
        try:
            if speaker_embedding is not None and audio_sample is not None:
@@ -263,7 +267,13 @@ def test_app(mocker: MockerFixture):
            if speaker_embedding is not None:
                result = await speech_server.upload_voice_embedding(speaker_embedding, consent, name)
            elif audio_sample is not None:
-                result = await speech_server.upload_voice(audio_sample, consent, name, ref_text=ref_text)
+                result = await speech_server.upload_voice(
+                    audio_sample,
+                    consent,
+                    name,
+                    ref_text=ref_text,
+                    speaker_description=speaker_description,
+                )
            else:
                raise ValueError("Either 'audio_sample' or 'speaker_embedding' must be provided")
            return {"success": True, "voice": result}
@@ -397,6 +407,44 @@ class TestSpeechAPI:
        assert result["voice"].get("ref_text") == "Hello world transcript"
        response = client.delete("/v1/audio/voices/test_voice_rt")

+    def test_upload_voice_with_speaker_description(self, client, tmp_path):
+        """Test voice upload with speaker_description stores and returns the description."""
+        # Pre-cleanup in case a previous test run left this voice behind
+        client.delete("/v1/audio/voices/test_voice_vd")
+
+        audio_content = b"fake audio content" * 1000
+        files = {"audio_sample": ("test.wav", audio_content, "audio/wav")}
+        data = {"consent": "c1", "name": "test_voice_vd", "speaker_description": "  warm, energetic narrator  "}
+
+        response = client.post("/v1/audio/voices", files=files, data=data)
+        try:
+            assert response.status_code == 200
+            result = response.json()
+            assert result["success"] is True
+            assert result["voice"]["name"] == "test_voice_vd"
+            assert result["voice"].get("speaker_description") == "warm, energetic narrator"
+        finally:
+            client.delete("/v1/audio/voices/test_voice_vd")
+
+    def test_upload_voice_speaker_description_in_listing(self, client):
+        """Test that speaker_description survives the upload → list round-trip."""
+        client.delete("/v1/audio/voices/test_voice_sd_list")
+
+        audio_content = b"fake audio content" * 1000
+        files = {"audio_sample": ("test.wav", audio_content, "audio/wav")}
+        data = {"consent": "c1", "name": "test_voice_sd_list", "speaker_description": "calm female narrator"}
+
+        response = client.post("/v1/audio/voices", files=files, data=data)
+        try:
+            assert response.status_code == 200
+
+            listing = client.get("/v1/audio/voices").json()
+            uploaded = {v["name"]: v for v in listing["uploaded_voices"]}
+            assert "test_voice_sd_list" in uploaded
+            assert uploaded["test_voice_sd_list"]["speaker_description"] == "calm female narrator"
+        finally:
+            client.delete("/v1/audio/voices/test_voice_sd_list")
+
    def test_upload_voice_file_too_large(self, client):
        """Test voice upload with file exceeding size limit."""
        # Create a file larger than 10MB
@@ -850,6 +898,7 @@ class TestTTSMethods:
                "file_path": "/tmp/voice_samples/custom_voice_consent_123.wav",
                "mime_type": "audio/wav",
                "ref_text": None,
+                "created_at": 1711234567.89,
            }
        }
        speech_server.supported_speakers = {"ryan", "vivian", "custom_voice"}
@@ -862,6 +911,7 @@ class TestTTSMethods:
            assert params["ref_audio"] == ["data:audio/wav;base64,ZmFrZWF1ZGlv"]
            assert params["x_vector_only_mode"] == [True]
            assert params["task_type"] == ["Base"]
+            assert params["voice_created_at"] == [1711234567.89]
            assert "ref_text" not in params

    def test_build_tts_params_with_uploaded_voice_ref_text(self, speech_server):
@@ -872,6 +922,7 @@ class TestTTSMethods:
                "file_path": "/tmp/voice_samples/custom_voice_consent_123.wav",
                "mime_type": "audio/wav",
                "ref_text": "Hello world transcript",
+                "created_at": 1711234567.89,
            }
        }
        speech_server.supported_speakers = {"ryan", "vivian", "custom_voice"}
@@ -885,6 +936,7 @@ class TestTTSMethods:
            assert params["x_vector_only_mode"] == [False]
            assert params["task_type"] == ["Base"]
            assert params["ref_text"] == ["Hello world transcript"]
+            assert params["voice_created_at"] == [1711234567.89]

    def test_build_tts_params_without_uploaded_voice(self, speech_server):
        """Test _build_tts_params does not auto-set ref_audio for non-uploaded voices."""
@@ -0,0 +1,129 @@
+import threading
+
+import pytest
+
+from vllm_omni.utils.voice_cache import VoiceEmbeddingCache
+
+pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
+
+
+@pytest.fixture
+def cache():
+    return VoiceEmbeddingCache(max_entries=4)
+
+
+class TestVoiceEmbeddingCache:
+    def test_miss_returns_none(self, cache: VoiceEmbeddingCache):
+        assert cache.get("nonexistent") is None
+        assert cache.stats()["misses"] == 1
+
+    def test_put_and_hit(self, cache: VoiceEmbeddingCache):
+        cache.put("abc", {"val": 42})
+        result = cache.get("abc")
+        assert result is not None
+        assert result["val"] == 42
+        assert cache.stats()["hits"] == 1
+
+    def test_lru_eviction(self, cache: VoiceEmbeddingCache):
+        for i in range(5):
+            cache.put(f"key{i}", {"i": i})
+        # key0 should have been evicted (oldest, max_entries=4)
+        assert cache.get("key0") is None
+        # key1..key4 should still be present
+        for i in range(1, 5):
+            assert cache.get(f"key{i}") is not None
+        assert cache.stats()["entries"] == 4
+
+    def test_lru_access_promotes(self, cache: VoiceEmbeddingCache):
+        cache.put("a", {"v": 1})
+        cache.put("b", {"v": 2})
+        cache.put("c", {"v": 3})
+        cache.put("d", {"v": 4})
+        # Access "a" to promote it to MRU
+        cache.get("a")
+        # Insert "e" -- should evict "b" (now the oldest), not "a"
+        cache.put("e", {"v": 5})
+        assert cache.get("a") is not None
+        assert cache.get("b") is None
+
+    def test_put_overwrites(self, cache: VoiceEmbeddingCache):
+        cache.put("k", {"old": True})
+        cache.put("k", {"new": True})
+        result = cache.get("k")
+        assert result is not None
+        assert "new" in result
+        assert "old" not in result
+        assert cache.stats()["entries"] == 1
+
+    def test_make_cache_key_includes_mode(self):
+        k1 = VoiceEmbeddingCache.make_cache_key("alice", xvec_only=True)
+        k2 = VoiceEmbeddingCache.make_cache_key("alice", xvec_only=False)
+        assert k1 != k2
+        assert "xvec" in k1
+        assert "icl" in k2
+
+    def test_make_cache_key_deterministic(self):
+        k1 = VoiceEmbeddingCache.make_cache_key("bob", xvec_only=True)
+        k2 = VoiceEmbeddingCache.make_cache_key("bob", xvec_only=True)
+        assert k1 == k2
+
+    def test_make_cache_key_created_at_isolation(self):
+        """Different created_at timestamps must produce different keys (stale-cache protection)."""
+        k1 = VoiceEmbeddingCache.make_cache_key("alice", xvec_only=False, created_at=1000.0)
+        k2 = VoiceEmbeddingCache.make_cache_key("alice", xvec_only=False, created_at=2000.0)
+        assert k1 != k2
+
+    def test_stale_cache_protection(self, cache: VoiceEmbeddingCache):
+        """Re-upload (new created_at) must produce a cache miss, not a stale hit."""
+        key_old = VoiceEmbeddingCache.make_cache_key("alice", xvec_only=False, created_at=1000.0)
+        key_new = VoiceEmbeddingCache.make_cache_key("alice", xvec_only=False, created_at=2000.0)
+        cache.put(key_old, {"ref_spk_embedding": "old_emb"})
+        # Re-upload produces a new created_at → different key → cold miss
+        assert cache.get(key_new) is None
+        # Old key still in cache (not yet evicted)
+        assert cache.get(key_old) is not None
+
+    def test_cache_mode_isolation(self, cache: VoiceEmbeddingCache):
+        """xvec entry must NOT be served for an icl request (same voice)."""
+        key_xvec = VoiceEmbeddingCache.make_cache_key("alice", xvec_only=True)
+        key_icl = VoiceEmbeddingCache.make_cache_key("alice", xvec_only=False)
+        cache.put(key_xvec, {"ref_code": None, "ref_spk_embedding": "emb"})
+        # icl request should miss — different key
+        assert cache.get(key_icl) is None
+        # xvec request should hit
+        assert cache.get(key_xvec) is not None
+
+    def test_stats_counters(self, cache: VoiceEmbeddingCache):
+        cache.put("x", {"v": 1})
+        cache.get("x")  # hit
+        cache.get("x")  # hit
+        cache.get("y")  # miss
+        s = cache.stats()
+        assert s["hits"] == 2
+        assert s["misses"] == 1
+        assert s["entries"] == 1
+        assert s["max_entries"] == 4
+
+    def test_thread_safety(self):
+        cache = VoiceEmbeddingCache(max_entries=32)
+        errors = []
+
+        def worker(thread_id: int):
+            try:
+                for i in range(50):
+                    key = f"t{thread_id}_k{i}"
+                    cache.put(key, {"tid": thread_id, "i": i})
+                    cache.get(key)
+                    cache.get(f"t{(thread_id + 1) % 10}_k{i}")
+            except Exception as e:
+                errors.append(e)
+
+        threads = [threading.Thread(target=worker, args=(t,)) for t in range(10)]
+        for t in threads:
+            t.start()
+        for t in threads:
+            t.join()
+
+        assert not errors, f"Thread safety errors: {errors}"
+        s = cache.stats()
+        assert s["entries"] <= 32