Complete cartoon presentation, Korean voice adoption and responsive art framing

2026-10-05 15:24:23 +09:00
parent a383bc9d13
commit bcc5c9a7b9
69 changed files with 7519 additions and 663 deletions
@@ -0,0 +1,79 @@
+{
+  "schemaVersion": 1,
+  "runId": "20261005T043059823226Z_abdd0294",
+  "createdUtc": "2026-10-05T04:30:59.826226+00:00",
+  "modelRevision": "0c0e3051f131929182e2c023b9537f8b1c68adfe",
+  "catalogHash": "c6bc24daadf42e2570959eb8f5578e113bb279dee3189ef43cbf084e88c54043",
+  "profileHash": "a5740d9db8a4aaebf08d0ac3b8f3225693f878aa2868143f01191a059e2680e8",
+  "scope": "selected",
+  "regenerateRequested": true,
+  "inputSnapshots": {
+    "catalog": "catalog.json",
+    "profile": "profile.json"
+  },
+  "requestedIds": [
+    "count_08"
+  ],
+  "environment": {
+    "python": "3.12.15 | packaged by Anaconda, Inc. | (main, Oct  1 2026, 20:14:50) [MSC v.1942 64 bit (AMD64)]",
+    "packages": {
+      "qwen-tts": "0.1.1",
+      "torch": "2.11.0+cu128",
+      "torchaudio": "2.11.0",
+      "transformers": "4.57.3",
+      "soundfile": "0.14.0",
+      "huggingface-hub": "0.36.2"
+    },
+    "device": "NVIDIA GeForce RTX 4080 SUPER",
+    "cuda": "12.8",
+    "modelDevice": "cuda:0",
+    "cudaProbe": 140.0,
+    "modelLoadSeconds": 4.906605000000127,
+    "modelPeakVramBytes": 4181138432,
+    "modelDefaults": {
+      "do_sample": true,
+      "repetition_penalty": 1.05,
+      "temperature": 0.9,
+      "top_p": 1.0,
+      "top_k": 50,
+      "subtalker_dosample": true,
+      "subtalker_temperature": 0.9,
+      "subtalker_top_p": 1.0,
+      "subtalker_top_k": 50,
+      "max_new_tokens": 8192
+    },
+    "effectiveGenerationParameters": {
+      "do_sample": true,
+      "top_k": 50,
+      "top_p": 1,
+      "temperature": 0.9,
+      "repetition_penalty": 1.05,
+      "subtalker_dosample": true,
+      "subtalker_top_k": 50,
+      "subtalker_top_p": 1,
+      "subtalker_temperature": 0.9,
+      "max_new_tokens": 8192
+    },
+    "peakVramBytes": 4227715072
+  },
+  "clips": [
+    {
+      "id": "count_08",
+      "textHash": "35f39a2c24f64215a55d8af9906d7acb5b29bb07ca2ec2f399125108f7e8d99b",
+      "settingsHash": "a5740d9db8a4aaebf08d0ac3b8f3225693f878aa2868143f01191a059e2680e8",
+      "originalRunId": "20261005T043059823226Z_abdd0294",
+      "file": "generated/20261005T043059823226Z_abdd0294/count_08.wav",
+      "review": "not_listened",
+      "sha256": "f9d6ca2574b12936d69da81af723a842a7fec8a3cf1b760e531eec58e4e07ad5",
+      "sampleRate": 24000,
+      "channels": 1,
+      "frames": 13440,
+      "duration": 0.56,
+      "peak": 0.392578125,
+      "rms": 0.08848943561315536,
+      "qualityWarnings": [],
+      "result": "generated",
+      "generationSeconds": 2.1404024999992544
+    }
+  ]
+}
@@ -0,0 +1,24 @@
+{
+  "schemaVersion": 1,
+  "modelId": "Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice",
+  "modelRevision": "0c0e3051f131929182e2c023b9537f8b1c68adfe",
+  "language": "Korean",
+  "speaker": "Sohee",
+  "instruct": "5~7세 아이에게 이야기하듯 따뜻하고 밝게, 천천히 또렷하게 읽어 주세요. 숫자는 정확하게 읽고 과장된 비명이나 웃음소리는 넣지 마세요.",
+  "device": "cuda:0",
+  "dtype": "bfloat16",
+  "attention": "sdpa",
+  "seed": 42,
+  "generationParameters": {
+    "do_sample": true,
+    "repetition_penalty": 1.05,
+    "temperature": 0.9,
+    "top_p": 1,
+    "top_k": 50,
+    "subtalker_dosample": true,
+    "subtalker_temperature": 0.9,
+    "subtalker_top_p": 1,
+    "subtalker_top_k": 50,
+    "max_new_tokens": 8192
+  }
+}