{
  "backend": "audiocpp-voxcpm2-tts",
  "configuration": {
    "audio_cpp_package": null,
    "audio_cpp_revision": "4af143229384fb6da3f373dc87de145ae954609b",
    "language": null,
    "package_format": "standalone GGUF with embedded model spec",
    "speaker_reference": "optional"
  },
  "created_at": "2026-09-17T22:55:16.012548+00:00",
  "family": "voxcpm2",
  "format": 2,
  "members": [
    {
      "bytes": 4772290272,
      "local_name": "voxcpm2-F16.gguf",
      "path": "voxcpm2-F16.gguf",
      "quant": "F16",
      "required": true,
      "role": "primary",
      "sha256": "0e623fb8bcf38e137f627897d03ca9997a4da685da035f36c9ee85f082e628bf"
    },
    {
      "bytes": 4772290272,
      "local_name": "voxcpm2-BF16.gguf",
      "path": "voxcpm2-BF16.gguf",
      "quant": "BF16",
      "required": true,
      "role": "primary",
      "sha256": "5c40a9a6a73ad68f9dcd285a6bbe59680f7db11d56f75a43d758d5cf648ed406"
    },
    {
      "bytes": 2955002464,
      "local_name": "voxcpm2-Q8_0.gguf",
      "path": "voxcpm2-Q8_0.gguf",
      "quant": "Q8_0",
      "required": true,
      "role": "primary",
      "sha256": "f60108e340fcaa0c7321932b92dbb620682dc8c2fb71f952e93d6cf0abe6b41a"
    },
    {
      "bytes": 1601496640,
      "local_name": "voxcpm2-Q3_K.gguf",
      "path": "voxcpm2-Q3_K.gguf",
      "quant": "Q3_K",
      "required": true,
      "role": "primary",
      "sha256": "da8958d42c44ea86ce77063c21ad0838cf201e71fa4a2349ed757b250dd90389"
    },
    {
      "bytes": 1885604448,
      "local_name": "voxcpm2-Q4_K.gguf",
      "path": "voxcpm2-Q4_K.gguf",
      "quant": "Q4_K",
      "required": true,
      "role": "primary",
      "sha256": "9ac7e046a06f60e2120b13e7483e8c097e4fdc042d12a969b7bfd8712407fe4d"
    },
    {
      "bytes": 2153000032,
      "local_name": "voxcpm2-Q5_K.gguf",
      "path": "voxcpm2-Q5_K.gguf",
      "quant": "Q5_K",
      "required": true,
      "role": "primary",
      "sha256": "effbac906a1419464a8e41f1d12c586255fb5cf19a51a259412a186a05c61a63"
    },
    {
      "bytes": 2437107840,
      "local_name": "voxcpm2-Q6_K.gguf",
      "path": "voxcpm2-Q6_K.gguf",
      "quant": "Q6_K",
      "required": true,
      "role": "primary",
      "sha256": "b4afefc7b5dc1da0ca61523670d062f1698aefac91b930161b7d4963ab375e74"
    }
  ],
  "model_format": "audiocpp-gguf",
  "quality": {
    "quants": {
      "BF16": {
        "clipping_ratio": 0.0,
        "first_audio_seconds": null,
        "fixtures": 5,
        "frames_per_second": null,
        "intelligibility_metric": "WER for whitespace scripts; CER for CJK",
        "minutes_per_audio_hour": 264.0,
        "passed": true,
        "performance_from_review": true,
        "real_time_factor": 4.4,
        "results": [
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 184320,
            "frames_per_second": null,
            "id": "numbers-punctuation-en",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/BF16/00-numbers-punctuation-en.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.133046,
            "roundtrip_wer": 0.111111,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.84,
            "silence_ratio": 0.158523,
            "text": "Version 3.1 costs 42 dollars; is that correct?",
            "transcript": "Version 3.1 costs $42. Is that correct?"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 384000,
            "frames_per_second": null,
            "id": "long-en",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/BF16/01-long-en.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.204059,
            "roundtrip_wer": 0.0,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 8.0,
            "silence_ratio": 0.082812,
            "text": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime.",
            "transcript": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime."
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 145920,
            "frames_per_second": null,
            "id": "short-fr",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/BF16/02-short-fr.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.160926,
            "roundtrip_wer": 0.142857,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.04,
            "silence_ratio": 0.097992,
            "text": "Bonjour, ceci est un test vocal multilingue.",
            "transcript": "Bonjour, ceci est un test vocal multilangue."
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 153600,
            "frames_per_second": null,
            "id": "short-ja",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/BF16/03-short-ja.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.193536,
            "roundtrip_wer": 0.055556,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.2,
            "silence_ratio": 0.150664,
            "text": "\u3053\u3093\u306b\u3061\u306f\u3001\u3053\u308c\u306f\u97f3\u58f0\u5408\u6210\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002",
            "transcript": "\u3053\u3093\u306b\u3061\u306f\u3002\u3053\u308c\u306f\u97f3\u58f0\u5408\u58f0\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 192000,
            "frames_per_second": null,
            "id": "short-zh",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/BF16/04-short-zh.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.099202,
            "roundtrip_wer": 0.5,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 4.0,
            "silence_ratio": 0.507698,
            "text": "\u4f60\u597d\uff0c\u8fd9\u662f\u4e00\u4e2a\u8bed\u97f3\u5408\u6210\u6d4b\u8bd5\u3002",
            "transcript": "\u4e5f\u597d\u9019\u662f\u4e00\u500b\u8a9e\u97f3\u5408\u6210\u6e2c\u8a66"
          }
        ],
        "resumed_from_artifacts": true,
        "roundtrip_wer": 0.161905,
        "silence_ratio": 0.507698
      },
      "F16": {
        "clipping_ratio": 0.0,
        "first_audio_seconds": 19.4324,
        "fixtures": 5,
        "frames_per_second": 10269.59,
        "intelligibility_metric": "WER for whitespace scripts; CER for CJK",
        "minutes_per_audio_hour": 290.35,
        "passed": true,
        "real_time_factor": 4.8391,
        "results": [
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "command": [
              "/home/linuxuser/.agentquantix/audio.cpp/build/bin/audiocpp_cli",
              "--task",
              "tts",
              "--family",
              "voxcpm2",
              "--model",
              "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/voxcpm2-F16.gguf",
              "--backend",
              "best",
              "--text",
              "Version 3.1 costs 42 dollars; is that correct?",
              "--out",
              "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/00-numbers-punctuation-en.wav",
              "--metrics",
              "--language",
              "en"
            ],
            "elapsed_seconds": 18.3029,
            "first_output_seconds": 18.1222,
            "frames": 168960,
            "frames_per_second": 9231.32,
            "id": "numbers-punctuation-en",
            "minutes_per_audio_hour": 311.98,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/00-numbers-punctuation-en.wav",
            "real_time_factor": 5.1997,
            "rms": 0.167574,
            "roundtrip_wer": 0.222222,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.52,
            "silence_ratio": 0.088394,
            "stdout": "family=voxcpm2\ntask=tts\nmode=offline\naudio_out=/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/00-numbers-punctuation-en.wav\nmetrics.wall_ms=15655.9\nmetrics.audio_duration_ms=3520\nmetrics.rtf=4.4477\nmetrics.x_realtime=0.224835\nmetrics.audio_duration_source=output\nmetrics.sample_rate=48000\nmetrics.channels=1\n",
            "text": "Version 3.1 costs 42 dollars; is that correct?",
            "transcript": "Fursion 3.1 costs $42. Is that correct?"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "command": [
              "/home/linuxuser/.agentquantix/audio.cpp/build/bin/audiocpp_cli",
              "--task",
              "tts",
              "--family",
              "voxcpm2",
              "--model",
              "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/voxcpm2-F16.gguf",
              "--backend",
              "best",
              "--text",
              "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime.",
              "--out",
              "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/01-long-en.wav",
              "--metrics",
              "--language",
              "en"
            ],
            "elapsed_seconds": 26.7112,
            "first_output_seconds": 26.5305,
            "frames": 384000,
            "frames_per_second": 14375.99,
            "id": "long-en",
            "minutes_per_audio_hour": 200.33,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/01-long-en.wav",
            "real_time_factor": 3.3389,
            "rms": 0.203471,
            "roundtrip_wer": 0.0,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 8.0,
            "silence_ratio": 0.083544,
            "stdout": "family=voxcpm2\ntask=tts\nmode=offline\naudio_out=/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/01-long-en.wav\nmetrics.wall_ms=23994.4\nmetrics.audio_duration_ms=8000\nmetrics.rtf=2.99929\nmetrics.x_realtime=0.333412\nmetrics.audio_duration_source=output\nmetrics.sample_rate=48000\nmetrics.channels=1\n",
            "text": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime.",
            "transcript": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime."
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "command": [
              "/home/linuxuser/.agentquantix/audio.cpp/build/bin/audiocpp_cli",
              "--task",
              "tts",
              "--family",
              "voxcpm2",
              "--model",
              "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/voxcpm2-F16.gguf",
              "--backend",
              "best",
              "--text",
              "Bonjour, ceci est un test vocal multilingue.",
              "--out",
              "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/02-short-fr.wav",
              "--metrics",
              "--language",
              "fr"
            ],
            "elapsed_seconds": 17.4925,
            "first_output_seconds": 17.3117,
            "frames": 145920,
            "frames_per_second": 8341.86,
            "id": "short-fr",
            "minutes_per_audio_hour": 345.25,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/02-short-fr.wav",
            "real_time_factor": 5.7541,
            "rms": 0.166584,
            "roundtrip_wer": 0.142857,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.04,
            "silence_ratio": 0.088172,
            "stdout": "family=voxcpm2\ntask=tts\nmode=offline\naudio_out=/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/02-short-fr.wav\nmetrics.wall_ms=14803.8\nmetrics.audio_duration_ms=3040\nmetrics.rtf=4.86966\nmetrics.x_realtime=0.205353\nmetrics.audio_duration_source=output\nmetrics.sample_rate=48000\nmetrics.channels=1\n",
            "text": "Bonjour, ceci est un test vocal multilingue.",
            "transcript": "Bonjour ! Ceci est un test vocal multilangue."
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "command": [
              "/home/linuxuser/.agentquantix/audio.cpp/build/bin/audiocpp_cli",
              "--task",
              "tts",
              "--family",
              "voxcpm2",
              "--model",
              "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/voxcpm2-F16.gguf",
              "--backend",
              "best",
              "--text",
              "\u3053\u3093\u306b\u3061\u306f\u3001\u3053\u308c\u306f\u97f3\u58f0\u5408\u6210\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002",
              "--out",
              "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/03-short-ja.wav",
              "--metrics",
              "--language",
              "ja"
            ],
            "elapsed_seconds": 16.2086,
            "first_output_seconds": 16.0279,
            "frames": 153600,
            "frames_per_second": 9476.45,
            "id": "short-ja",
            "minutes_per_audio_hour": 303.91,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/03-short-ja.wav",
            "real_time_factor": 5.0652,
            "rms": 0.194407,
            "roundtrip_wer": 0.055556,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.2,
            "silence_ratio": 0.162826,
            "stdout": "family=voxcpm2\ntask=tts\nmode=offline\naudio_out=/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/03-short-ja.wav\nmetrics.wall_ms=13493.4\nmetrics.audio_duration_ms=3200\nmetrics.rtf=4.21668\nmetrics.x_realtime=0.237153\nmetrics.audio_duration_source=output\nmetrics.sample_rate=48000\nmetrics.channels=1\n",
            "text": "\u3053\u3093\u306b\u3061\u306f\u3001\u3053\u308c\u306f\u97f3\u58f0\u5408\u6210\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002",
            "transcript": "\u3053\u3093\u306b\u3061\u306f\u3002\u3053\u308c\u306f\u97f3\u58f0\u5408\u6027\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "command": [
              "/home/linuxuser/.agentquantix/audio.cpp/build/bin/audiocpp_cli",
              "--task",
              "tts",
              "--family",
              "voxcpm2",
              "--model",
              "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/voxcpm2-F16.gguf",
              "--backend",
              "best",
              "--text",
              "\u4f60\u597d\uff0c\u8fd9\u662f\u4e00\u4e2a\u8bed\u97f3\u5408\u6210\u6d4b\u8bd5\u3002",
              "--out",
              "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/04-short-zh.wav",
              "--metrics",
              "--language",
              "zh"
            ],
            "elapsed_seconds": 19.3503,
            "first_output_seconds": 19.1696,
            "frames": 192000,
            "frames_per_second": 9922.33,
            "id": "short-zh",
            "minutes_per_audio_hour": 290.26,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/04-short-zh.wav",
            "real_time_factor": 4.8376,
            "rms": 0.097418,
            "roundtrip_wer": 0.5,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 4.0,
            "silence_ratio": 0.506927,
            "stdout": "family=voxcpm2\ntask=tts\nmode=offline\naudio_out=/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/F16/04-short-zh.wav\nmetrics.wall_ms=16673.3\nmetrics.audio_duration_ms=4000\nmetrics.rtf=4.16832\nmetrics.x_realtime=0.239905\nmetrics.audio_duration_source=output\nmetrics.sample_rate=48000\nmetrics.channels=1\n",
            "text": "\u4f60\u597d\uff0c\u8fd9\u662f\u4e00\u4e2a\u8bed\u97f3\u5408\u6210\u6d4b\u8bd5\u3002",
            "transcript": "\u4e5f\u597d\u9019\u662f\u4e00\u500b\u8a9e\u97f3\u5408\u6210\u6e2c\u8a66"
          }
        ],
        "roundtrip_wer": 0.184127,
        "silence_ratio": 0.506927
      },
      "Q3_K": {
        "clipping_ratio": 0.0,
        "first_audio_seconds": null,
        "fixtures": 5,
        "frames_per_second": null,
        "intelligibility_metric": "WER for whitespace scripts; CER for CJK",
        "minutes_per_audio_hour": 324.0,
        "passed": true,
        "performance_from_review": true,
        "real_time_factor": 5.4,
        "results": [
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 192000,
            "frames_per_second": null,
            "id": "numbers-punctuation-en",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q3_K/00-numbers-punctuation-en.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.326681,
            "roundtrip_wer": 0.111111,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 4.0,
            "silence_ratio": 0.025245,
            "text": "Version 3.1 costs 42 dollars; is that correct?",
            "transcript": "version 3.1 cost 42 dollars. Is that correct?"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 453120,
            "frames_per_second": null,
            "id": "long-en",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q3_K/01-long-en.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.380062,
            "roundtrip_wer": 0.047619,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 9.44,
            "silence_ratio": 0.034194,
            "text": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime.",
            "transcript": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion files required by the runtime."
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 192000,
            "frames_per_second": null,
            "id": "short-fr",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q3_K/02-short-fr.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.272483,
            "roundtrip_wer": 0.428571,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 4.0,
            "silence_ratio": 0.039297,
            "text": "Bonjour, ceci est un test vocal multilingue.",
            "transcript": "Bonjour ! Ceci est un des vacales m\u00e9decines."
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 153600,
            "frames_per_second": null,
            "id": "short-ja",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q3_K/03-short-ja.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.307624,
            "roundtrip_wer": 0.055556,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.2,
            "silence_ratio": 0.126797,
            "text": "\u3053\u3093\u306b\u3061\u306f\u3001\u3053\u308c\u306f\u97f3\u58f0\u5408\u6210\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002",
            "transcript": "\u3053\u3093\u306b\u3061\u306f\u3002\u3053\u308c\u306f\u97f3\u58f0\u5408\u58f0\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 153600,
            "frames_per_second": null,
            "id": "short-zh",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q3_K/04-short-zh.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.186435,
            "roundtrip_wer": 0.333333,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.2,
            "silence_ratio": 0.233431,
            "text": "\u4f60\u597d\uff0c\u8fd9\u662f\u4e00\u4e2a\u8bed\u97f3\u5408\u6210\u6d4b\u8bd5\u3002",
            "transcript": "\u4f60\u597d,\u8fd9\u662f\u4e00\u4e2a\u9c7c\u548c\u57ce\u6d4b\u8bd5"
          }
        ],
        "resumed_from_artifacts": true,
        "roundtrip_wer": 0.195238,
        "silence_ratio": 0.233431
      },
      "Q4_K": {
        "clipping_ratio": 0.0,
        "first_audio_seconds": null,
        "fixtures": 5,
        "frames_per_second": null,
        "intelligibility_metric": "WER for whitespace scripts; CER for CJK",
        "minutes_per_audio_hour": 300.0,
        "passed": true,
        "performance_from_review": true,
        "real_time_factor": 5.0,
        "results": [
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 161280,
            "frames_per_second": null,
            "id": "numbers-punctuation-en",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q4_K/00-numbers-punctuation-en.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.198127,
            "roundtrip_wer": 0.111111,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.36,
            "silence_ratio": 0.084524,
            "text": "Version 3.1 costs 42 dollars; is that correct?",
            "transcript": "Version 3.1 costs $42. Is that correct?"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 376320,
            "frames_per_second": null,
            "id": "long-en",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q4_K/01-long-en.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.196146,
            "roundtrip_wer": 0.0,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 7.84,
            "silence_ratio": 0.07702,
            "text": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime.",
            "transcript": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime."
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 168960,
            "frames_per_second": null,
            "id": "short-fr",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q4_K/02-short-fr.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.131053,
            "roundtrip_wer": 0.142857,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.52,
            "silence_ratio": 0.075059,
            "text": "Bonjour, ceci est un test vocal multilingue.",
            "transcript": "Bonjour ! Ceci est un test vocal multilangue !"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 130560,
            "frames_per_second": null,
            "id": "short-ja",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q4_K/03-short-ja.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.23994,
            "roundtrip_wer": 0.055556,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 2.72,
            "silence_ratio": 0.128661,
            "text": "\u3053\u3093\u306b\u3061\u306f\u3001\u3053\u308c\u306f\u97f3\u58f0\u5408\u6210\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002",
            "transcript": "\u3053\u3093\u306b\u3061\u306f\u3002\u3053\u308c\u306f\u97f3\u58f0\u5408\u58f0\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 153600,
            "frames_per_second": null,
            "id": "short-zh",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q4_K/04-short-zh.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.163529,
            "roundtrip_wer": 0.25,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.2,
            "silence_ratio": 0.244212,
            "text": "\u4f60\u597d\uff0c\u8fd9\u662f\u4e00\u4e2a\u8bed\u97f3\u5408\u6210\u6d4b\u8bd5\u3002",
            "transcript": "\u60a8\u597d \u8fd9\u662f\u4e00\u4e2a\u4e0e\u4e91\u5408\u6210\u6d4b\u8bd5"
          }
        ],
        "resumed_from_artifacts": true,
        "roundtrip_wer": 0.111905,
        "silence_ratio": 0.244212
      },
      "Q5_K": {
        "clipping_ratio": 0.0,
        "first_audio_seconds": null,
        "fixtures": 5,
        "frames_per_second": null,
        "intelligibility_metric": "WER for whitespace scripts; CER for CJK",
        "minutes_per_audio_hour": 342.0,
        "passed": true,
        "performance_from_review": true,
        "real_time_factor": 5.7,
        "results": [
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 238080,
            "frames_per_second": null,
            "id": "numbers-punctuation-en",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q5_K/00-numbers-punctuation-en.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.120141,
            "roundtrip_wer": 0.111111,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 4.96,
            "silence_ratio": 0.153385,
            "text": "Version 3.1 costs 42 dollars; is that correct?",
            "transcript": "version 3.1 costs $42. Is that correct?"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 384000,
            "frames_per_second": null,
            "id": "long-en",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q5_K/01-long-en.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.19138,
            "roundtrip_wer": 0.0,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 8.0,
            "silence_ratio": 0.089805,
            "text": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime.",
            "transcript": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime."
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 192000,
            "frames_per_second": null,
            "id": "short-fr",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q5_K/02-short-fr.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.163489,
            "roundtrip_wer": 0.142857,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 4.0,
            "silence_ratio": 0.110068,
            "text": "Bonjour, ceci est un test vocal multilingue.",
            "transcript": "Bonjour ! Ceci est un test vocal multilangue."
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 130560,
            "frames_per_second": null,
            "id": "short-ja",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q5_K/03-short-ja.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.174939,
            "roundtrip_wer": 0.111111,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 2.72,
            "silence_ratio": 0.088496,
            "text": "\u3053\u3093\u306b\u3061\u306f\u3001\u3053\u308c\u306f\u97f3\u58f0\u5408\u6210\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002",
            "transcript": "\u3053\u3093\u306b\u3061\u306f\u3002\u3053\u308c\u306f\u97f3\u58f0\u9ad8\u58f0\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 161280,
            "frames_per_second": null,
            "id": "short-zh",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q5_K/04-short-zh.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.101781,
            "roundtrip_wer": 0.166667,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.36,
            "silence_ratio": 0.456262,
            "text": "\u4f60\u597d\uff0c\u8fd9\u662f\u4e00\u4e2a\u8bed\u97f3\u5408\u6210\u6d4b\u8bd5\u3002",
            "transcript": "\u4f60\u597d \u8fd9\u662f\u4e00\u4e2a\u8bed\u97f3\u548c\u8bda\u6d4b\u8bd5"
          }
        ],
        "resumed_from_artifacts": true,
        "roundtrip_wer": 0.106349,
        "silence_ratio": 0.456262
      },
      "Q6_K": {
        "clipping_ratio": 0.0,
        "first_audio_seconds": null,
        "fixtures": 5,
        "frames_per_second": null,
        "intelligibility_metric": "WER for whitespace scripts; CER for CJK",
        "minutes_per_audio_hour": 300.0,
        "passed": true,
        "performance_from_review": true,
        "real_time_factor": 5.0,
        "results": [
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 207360,
            "frames_per_second": null,
            "id": "numbers-punctuation-en",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q6_K/00-numbers-punctuation-en.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.157859,
            "roundtrip_wer": 0.111111,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 4.32,
            "silence_ratio": 0.193475,
            "text": "Version 3.1 costs 42 dollars; is that correct?",
            "transcript": "Version 3.1 costs $42. Is that correct?"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 384000,
            "frames_per_second": null,
            "id": "long-en",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q6_K/01-long-en.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.21542,
            "roundtrip_wer": 0.0,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 8.0,
            "silence_ratio": 0.073685,
            "text": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime.",
            "transcript": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime."
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 153600,
            "frames_per_second": null,
            "id": "short-fr",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q6_K/02-short-fr.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.188378,
            "roundtrip_wer": 0.142857,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.2,
            "silence_ratio": 0.055319,
            "text": "Bonjour, ceci est un test vocal multilingue.",
            "transcript": "Bonjour ! Ceci est un test vocal multilangue !"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 161280,
            "frames_per_second": null,
            "id": "short-ja",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q6_K/03-short-ja.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.198035,
            "roundtrip_wer": 0.055556,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.36,
            "silence_ratio": 0.124709,
            "text": "\u3053\u3093\u306b\u3061\u306f\u3001\u3053\u308c\u306f\u97f3\u58f0\u5408\u6210\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002",
            "transcript": "\u3053\u3093\u306b\u3061\u306f\u3002\u3053\u308c\u306f\u97f3\u58f0\u5408\u6027\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 215040,
            "frames_per_second": null,
            "id": "short-zh",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q6_K/04-short-zh.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.128449,
            "roundtrip_wer": 0.5,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 4.48,
            "silence_ratio": 0.510324,
            "text": "\u4f60\u597d\uff0c\u8fd9\u662f\u4e00\u4e2a\u8bed\u97f3\u5408\u6210\u6d4b\u8bd5\u3002",
            "transcript": "\u4e5f\u597d \u9019\u662f\u4e00\u500b\u8a9e\u97f3\u5408\u6210\u6e2c\u8a66"
          }
        ],
        "resumed_from_artifacts": true,
        "roundtrip_wer": 0.161905,
        "silence_ratio": 0.510324
      },
      "Q8_0": {
        "clipping_ratio": 0.0,
        "first_audio_seconds": null,
        "fixtures": 5,
        "frames_per_second": null,
        "intelligibility_metric": "WER for whitespace scripts; CER for CJK",
        "minutes_per_audio_hour": 300.0,
        "passed": true,
        "performance_from_review": true,
        "real_time_factor": 5.0,
        "results": [
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 184320,
            "frames_per_second": null,
            "id": "numbers-punctuation-en",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q8_0/00-numbers-punctuation-en.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.179811,
            "roundtrip_wer": 0.111111,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.84,
            "silence_ratio": 0.148492,
            "text": "Version 3.1 costs 42 dollars; is that correct?",
            "transcript": "version 3.1 costs $42. Is that correct?"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 384000,
            "frames_per_second": null,
            "id": "long-en",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q8_0/01-long-en.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.20168,
            "roundtrip_wer": 0.0,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 8.0,
            "silence_ratio": 0.07607,
            "text": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime.",
            "transcript": "A reliable voice release must produce clear audio, preserve punctuation and numbers, and include every companion file required by the runtime."
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 145920,
            "frames_per_second": null,
            "id": "short-fr",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q8_0/02-short-fr.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.179413,
            "roundtrip_wer": 0.142857,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.04,
            "silence_ratio": 0.067989,
            "text": "Bonjour, ceci est un test vocal multilingue.",
            "transcript": "Bonjour ! Ceci est un test vocal multilangue."
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 153600,
            "frames_per_second": null,
            "id": "short-ja",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q8_0/03-short-ja.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.202345,
            "roundtrip_wer": 0.055556,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 3.2,
            "silence_ratio": 0.166836,
            "text": "\u3053\u3093\u306b\u3061\u306f\u3001\u3053\u308c\u306f\u97f3\u58f0\u5408\u6210\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002",
            "transcript": "\u3053\u3093\u306b\u3061\u306f\u3002\u3053\u308c\u306f\u97f3\u58f0\u5408\u6027\u306e\u30c6\u30b9\u30c8\u3067\u3059\u3002"
          },
          {
            "channels": 1,
            "clipping_ratio": 0.0,
            "first_output_seconds": null,
            "frames": 215040,
            "frames_per_second": null,
            "id": "short-zh",
            "minutes_per_audio_hour": null,
            "path": "/home/linuxuser/.agentquantix/temp/voice/openbmb--VoxCPM2/models/quality/Q8_0/04-short-zh.wav",
            "real_time_factor": null,
            "resumed_from_artifacts": true,
            "rms": 0.120478,
            "roundtrip_wer": 0.5,
            "sample_rate": 48000,
            "sample_width": 2,
            "seconds": 4.48,
            "silence_ratio": 0.497661,
            "text": "\u4f60\u597d\uff0c\u8fd9\u662f\u4e00\u4e2a\u8bed\u97f3\u5408\u6210\u6d4b\u8bd5\u3002",
            "transcript": "\u4e5f\u597d\u9019\u662f\u4e00\u500b\u8a9e\u97f3\u5408\u6210\u6e2c\u8a66"
          }
        ],
        "resumed_from_artifacts": true,
        "roundtrip_wer": 0.161905,
        "silence_ratio": 0.497661
      }
    }
  },
  "quant": null,
  "runtime": "audiocpp_cli",
  "source_repo": "openbmb/VoxCPM2",
  "source_revision": "32279effe8c19989596f05d353d1447f51d9e915",
  "track": "tts"
}