Add verified browser ONNX export

README.md

@@ -28,6 +28,8 @@ This release selects the checkpoint at **global step 50,000** (`val_mel = 0.3951
 - Generator parameters: approximately 23.7M
 - Full trainable checkpoint: `checkpoint/gooya-rizehpizeh-v2-step50000-val_mel0.3951.ckpt`
 - Checkpoint SHA-256: `0c2d22718894e20fb6361c7bf2d75ee54d61db3a167983ce5d843ff6ed438938`
+- Browser/Piper model: `gooya-rizehpizeh-v2.onnx`
+- Browser/Piper model SHA-256: `675c557524a325cc014e27acb7bb9f7eab584d3247216f934e8a378b709a2d3b`
 - Sample rate: 22,050 Hz
 - Speakers: 1
 - Phoneme type: `text`
@@ -71,6 +73,18 @@ Audio timing came from AvaSanj v1 CTC forced alignment. Training phoneme labels
 
 The 100K run was resumed from a successful 2K signal checkpoint. The sealed 669-parent eval split was not used for checkpoint selection.
 
+## ONNX and browser validation
+
+The selected checkpoint was exported twice with Piper's ONNX exporter. Both exports were byte-identical. The published ONNX is self-contained and has no external tensor-data file.
+
+- File size: `63,516,051` bytes
+- Inputs: `input` (`int64`, `[batch, phonemes]`), `input_lengths` (`int64`, `[batch]`), `scales` (`float32`, `[3]`)
+- Output: `output` (`float32`, dynamic audio length)
+- ONNX Runtime CPU probes: 19/19 finite, positive-length outputs
+- Gouya.app `onnxruntime-web@1.27.0` WASM smoke test: passed using the application's real `rizehPhoneTextToIds` mapping
+
+Machine-readable receipts are in `browser/`.
+
 ## Inference and long-form use
 
 Input must already be case-sensitive Negara-compatible phonetic text. Example:
@@ -90,7 +104,7 @@ For long-form narration, do not send an article as one model input. Split at sem
 - G2P/Finglish quality remains the dominant source of pronunciation errors.
 - Very long single-pass phoneme sequences can collapse or omit content; use chunked synthesis.
 - Overly small chunks sound breathy and robotic. Prefer substantial semantic spans instead of fixed tiny fragments.
-- This release has not yet been promoted over v1.5 on Gouya.app.
+- Browser export validation does not by itself constitute live Gouya.app promotion; the deployed consumer path must still be tested after rollout.
 
 ## License
 

browser/browser-wasm-smoke-report.json

@@ -0,0 +1,19 @@
+{
+  "duration_seconds": 2.9373242630385485,
+  "finite": true,
+  "input_ids": 131,
+  "model_sha256": "675c557524a325cc014e27acb7bb9f7eab584d3247216f934e8a378b709a2d3b",
+  "output_dims": [
+    1,
+    1,
+    1,
+    64768
+  ],
+  "output_samples": 64768,
+  "peak": 0.7937009930610657,
+  "provider": "wasm",
+  "runtime": "onnxruntime-web@1.27.0",
+  "schema_version": "gooya.rizehpizeh-v2-browser-smoke/v1",
+  "status": "accepted",
+  "test_phone_text": "zurxAneye vahdat yek makAne varzeSi dar Sahre borujerd ast."
+}

browser/onnx-export-report.json

@@ -0,0 +1,314 @@
+{
+  "bytes": 63516051,
+  "config_sha256": "981770210ac1aea618cb8134597127911051deabf9900824df3388f209a884fa",
+  "deterministic_scales": [
+    0.0,
+    1.0,
+    0.0
+  ],
+  "external_data": false,
+  "inputs": [
+    {
+      "name": "input",
+      "shape": [
+        "batch_size",
+        "phonemes"
+      ],
+      "type": "tensor(int64)"
+    },
+    {
+      "name": "input_lengths",
+      "shape": [
+        "batch_size"
+      ],
+      "type": "tensor(int64)"
+    },
+    {
+      "name": "scales",
+      "shape": [
+        3
+      ],
+      "type": "tensor(float)"
+    }
+  ],
+  "ir_version": 8,
+  "onnx_sha256": "675c557524a325cc014e27acb7bb9f7eab584d3247216f934e8a378b709a2d3b",
+  "opsets": [
+    {
+      "domain": "",
+      "version": 15
+    }
+  ],
+  "outputs": [
+    {
+      "name": "output",
+      "shape": [
+        "batch_size",
+        1,
+        1,
+        "Unsqueezeoutput_dim_3"
+      ],
+      "type": "tensor(float)"
+    }
+  ],
+  "providers": [
+    "CPUExecutionProvider"
+  ],
+  "rows": [
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        137728
+      ],
+      "peak": 0.8556598424911499,
+      "phone_ids": 321,
+      "samples": 137728,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0014-11c7af4978b2--000.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        133888
+      ],
+      "peak": 0.7498155236244202,
+      "phone_ids": 319,
+      "samples": 133888,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0014-11c7af4978b2--001.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        136448
+      ],
+      "peak": 0.8162416219711304,
+      "phone_ids": 287,
+      "samples": 136448,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0014-11c7af4978b2--002.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        129280
+      ],
+      "peak": 0.7922796010971069,
+      "phone_ids": 325,
+      "samples": 129280,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0014-11c7af4978b2--003.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        141312
+      ],
+      "peak": 0.8399786353111267,
+      "phone_ids": 217,
+      "samples": 141312,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0014-11c7af4978b2--004.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        147456
+      ],
+      "peak": 0.839239776134491,
+      "phone_ids": 253,
+      "samples": 147456,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0014-11c7af4978b2--005.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        62464
+      ],
+      "peak": 0.8430166244506836,
+      "phone_ids": 113,
+      "samples": 62464,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0014-11c7af4978b2--006.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        150016
+      ],
+      "peak": 0.8254867792129517,
+      "phone_ids": 407,
+      "samples": 150016,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0020-badd7f9a1cf9--000.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        84480
+      ],
+      "peak": 0.8269263505935669,
+      "phone_ids": 197,
+      "samples": 84480,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0020-badd7f9a1cf9--001.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        135680
+      ],
+      "peak": 0.7935409545898438,
+      "phone_ids": 301,
+      "samples": 135680,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0020-badd7f9a1cf9--002.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        122880
+      ],
+      "peak": 0.8605506420135498,
+      "phone_ids": 235,
+      "samples": 122880,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0020-badd7f9a1cf9--003.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        122624
+      ],
+      "peak": 0.7984231114387512,
+      "phone_ids": 289,
+      "samples": 122624,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0020-badd7f9a1cf9--004.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        142336
+      ],
+      "peak": 0.8614963293075562,
+      "phone_ids": 321,
+      "samples": 142336,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0020-badd7f9a1cf9--005.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        48384
+      ],
+      "peak": 0.8291678428649902,
+      "phone_ids": 99,
+      "samples": 48384,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0020-badd7f9a1cf9--006.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        118784
+      ],
+      "peak": 0.7483747005462646,
+      "phone_ids": 305,
+      "samples": 118784,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0021-d0f01be99058--000.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        141056
+      ],
+      "peak": 0.8492122888565063,
+      "phone_ids": 323,
+      "samples": 141056,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0021-d0f01be99058--001.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        151552
+      ],
+      "peak": 0.7924327254295349,
+      "phone_ids": 277,
+      "samples": 151552,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0021-d0f01be99058--002.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        133120
+      ],
+      "peak": 0.8153193593025208,
+      "phone_ids": 291,
+      "samples": 133120,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0021-d0f01be99058--003.flac"
+    },
+    {
+      "finite": true,
+      "output_shape": [
+        1,
+        1,
+        1,
+        118528
+      ],
+      "peak": 0.7740210890769958,
+      "phone_ids": 267,
+      "samples": 118528,
+      "utterance": "/home/rezo/piper-wikipedia-approved-20260830/data/aligned-full-v1/audio/eval/wiki-fa-0021-d0f01be99058--004.flac"
+    }
+  ],
+  "schema_version": "gooya.rizehpizeh-v2-onnx-export/v1",
+  "source_checkpoint_sha256": "0c2d22718894e20fb6361c7bf2d75ee54d61db3a167983ce5d843ff6ed438938",
+  "status": "accepted",
+  "summary": {
+    "finite_rows": 19,
+    "positive_length_rows": 19,
+    "rows": 19
+  }
+}

gooya-rizehpizeh-v2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:675c557524a325cc014e27acb7bb9f7eab584d3247216f934e8a378b709a2d3b
+size 63516051

gooya-rizehpizeh-v2.onnx.json

@@ -0,0 +1,518 @@
+{
+  "audio": {
+    "sample_rate": 22050
+  },
+  "espeak": {
+    "voice": "fa"
+  },
+  "phoneme_type": "text",
+  "num_symbols": 256,
+  "num_speakers": 1,
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1.0,
+    "noise_w": 0.8
+  },
+  "phoneme_id_map": {
+    " ": [
+      3
+    ],
+    "!": [
+      4
+    ],
+    "\"": [
+      150
+    ],
+    "#": [
+      149
+    ],
+    "$": [
+      2
+    ],
+    "'": [
+      5
+    ],
+    "(": [
+      6
+    ],
+    ")": [
+      7
+    ],
+    ",": [
+      8
+    ],
+    "-": [
+      9
+    ],
+    ".": [
+      10
+    ],
+    "0": [
+      130
+    ],
+    "1": [
+      131
+    ],
+    "2": [
+      132
+    ],
+    "3": [
+      133
+    ],
+    "4": [
+      134
+    ],
+    "5": [
+      135
+    ],
+    "6": [
+      136
+    ],
+    "7": [
+      137
+    ],
+    "8": [
+      138
+    ],
+    "9": [
+      139
+    ],
+    ":": [
+      11
+    ],
+    ";": [
+      12
+    ],
+    "?": [
+      109
+    ],
+    "A": [
+      52,
+      0,
+      122
+    ],
+    "C": [
+      32,
+      0,
+      96
+    ],
+    "Q": [
+      109
+    ],
+    "S": [
+      96
+    ],
+    "X": [
+      156
+    ],
+    "Z": [
+      108
+    ],
+    "^": [
+      1
+    ],
+    "_": [
+      0
+    ],
+    "a": [
+      39
+    ],
+    "b": [
+      15
+    ],
+    "c": [
+      16
+    ],
+    "d": [
+      17
+    ],
+    "e": [
+      18
+    ],
+    "f": [
+      19
+    ],
+    "g": [
+      66
+    ],
+    "h": [
+      20
+    ],
+    "i": [
+      21,
+      0,
+      122
+    ],
+    "j": [
+      17,
+      0,
+      108
+    ],
+    "k": [
+      23
+    ],
+    "l": [
+      24
+    ],
+    "m": [
+      25
+    ],
+    "n": [
+      26
+    ],
+    "o": [
+      27
+    ],
+    "p": [
+      28
+    ],
+    "q": [
+      68
+    ],
+    "r": [
+      92
+    ],
+    "s": [
+      31
+    ],
+    "t": [
+      32
+    ],
+    "u": [
+      33,
+      0,
+      122
+    ],
+    "v": [
+      34
+    ],
+    "w": [
+      35
+    ],
+    "x": [
+      36
+    ],
+    "y": [
+      22
+    ],
+    "z": [
+      38
+    ],
+    "æ": [
+      39
+    ],
+    "ç": [
+      40
+    ],
+    "ð": [
+      41
+    ],
+    "ø": [
+      42
+    ],
+    "ħ": [
+      43
+    ],
+    "ŋ": [
+      44
+    ],
+    "œ": [
+      45
+    ],
+    "ǀ": [
+      46
+    ],
+    "ǁ": [
+      47
+    ],
+    "ǂ": [
+      48
+    ],
+    "ǃ": [
+      49
+    ],
+    "ɐ": [
+      50
+    ],
+    "ɑ": [
+      51
+    ],
+    "ɒ": [
+      52
+    ],
+    "ɓ": [
+      53
+    ],
+    "ɔ": [
+      54
+    ],
+    "ɕ": [
+      55
+    ],
+    "ɖ": [
+      56
+    ],
+    "ɗ": [
+      57
+    ],
+    "ɘ": [
+      58
+    ],
+    "ə": [
+      59
+    ],
+    "ɚ": [
+      60
+    ],
+    "ɛ": [
+      61
+    ],
+    "ɜ": [
+      62
+    ],
+    "ɞ": [
+      63
+    ],
+    "ɟ": [
+      64
+    ],
+    "ɠ": [
+      65
+    ],
+    "ɡ": [
+      66
+    ],
+    "ɢ": [
+      67
+    ],
+    "ɣ": [
+      68
+    ],
+    "ɤ": [
+      69
+    ],
+    "ɥ": [
+      70
+    ],
+    "ɦ": [
+      71
+    ],
+    "ɧ": [
+      72
+    ],
+    "ɨ": [
+      73
+    ],
+    "ɪ": [
+      74
+    ],
+    "ɫ": [
+      75
+    ],
+    "ɬ": [
+      76
+    ],
+    "ɭ": [
+      77
+    ],
+    "ɮ": [
+      78
+    ],
+    "ɯ": [
+      79
+    ],
+    "ɰ": [
+      80
+    ],
+    "ɱ": [
+      81
+    ],
+    "ɲ": [
+      82
+    ],
+    "ɳ": [
+      83
+    ],
+    "ɴ": [
+      84
+    ],
+    "ɵ": [
+      85
+    ],
+    "ɶ": [
+      86
+    ],
+    "ɸ": [
+      87
+    ],
+    "ɹ": [
+      88
+    ],
+    "ɺ": [
+      89
+    ],
+    "ɻ": [
+      90
+    ],
+    "ɽ": [
+      91
+    ],
+    "ɾ": [
+      92
+    ],
+    "ʀ": [
+      93
+    ],
+    "ʁ": [
+      94
+    ],
+    "ʂ": [
+      95
+    ],
+    "ʃ": [
+      96
+    ],
+    "ʄ": [
+      97
+    ],
+    "ʈ": [
+      98
+    ],
+    "ʉ": [
+      99
+    ],
+    "ʊ": [
+      100
+    ],
+    "ʋ": [
+      101
+    ],
+    "ʌ": [
+      102
+    ],
+    "ʍ": [
+      103
+    ],
+    "ʎ": [
+      104
+    ],
+    "ʏ": [
+      105
+    ],
+    "ʐ": [
+      106
+    ],
+    "ʑ": [
+      107
+    ],
+    "ʒ": [
+      108
+    ],
+    "ʔ": [
+      109
+    ],
+    "ʕ": [
+      110
+    ],
+    "ʘ": [
+      111
+    ],
+    "ʙ": [
+      112
+    ],
+    "ʛ": [
+      113
+    ],
+    "ʜ": [
+      114
+    ],
+    "ʝ": [
+      115
+    ],
+    "ʟ": [
+      116
+    ],
+    "ʡ": [
+      117
+    ],
+    "ʢ": [
+      118
+    ],
+    "ʦ": [
+      155
+    ],
+    "ʰ": [
+      145
+    ],
+    "ʲ": [
+      119
+    ],
+    "ˈ": [
+      120
+    ],
+    "ˌ": [
+      121
+    ],
+    "ː": [
+      122
+    ],
+    "ˑ": [
+      123
+    ],
+    "˞": [
+      124
+    ],
+    "ˤ": [
+      146
+    ],
+    "̃": [
+      141
+    ],
+    "̧": [
+      140
+    ],
+    "̩": [
+      144
+    ],
+    "̪": [
+      142
+    ],
+    "̯": [
+      143
+    ],
+    "̺": [
+      152
+    ],
+    "̻": [
+      153
+    ],
+    "β": [
+      125
+    ],
+    "ε": [
+      147
+    ],
+    "θ": [
+      126
+    ],
+    "χ": [
+      127
+    ],
+    "ᵻ": [
+      128
+    ],
+    "↑": [
+      151
+    ],
+    "↓": [
+      148
+    ],
+    "ⱱ": [
+      129
+    ]
+  },
+  "speaker_id_map": {},
+  "hop_length": 256,
+  "default_speaker_id": 0,
+  "piper_version": "1.5.0"
+}

release-manifest.json

@@ -11,9 +11,19 @@
       "sha256": "beacc839712cc8db59ad2997b52edb77946461593219d82276e39ba7e404f7ef"
     },
     {
-      "bytes": 4057,
+      "bytes": 4933,
       "path": "README.md",
-      "sha256": "997ae579d683bead1b159189bf598202a4fdee03122c90132d06857f823d443e"
+      "sha256": "8699cb2c567fb8c0c4a52ea9e0edb691bbd79c7f44d81b1b52f75bdaf10e3439"
+    },
+    {
+      "bytes": 510,
+      "path": "browser/browser-wasm-smoke-report.json",
+      "sha256": "ce1202b0675cf3c72944334bb1fbd61997af34e7ddc2d15166fd35b617cd54a0"
+    },
+    {
+      "bytes": 7588,
+      "path": "browser/onnx-export-report.json",
+      "sha256": "e1812cdfd6dd31768245b90f13e47b6785346e9f1b09083cb6bfd57b7d093d0f"
     },
     {
       "bytes": 845890322,
@@ -25,6 +35,16 @@
       "path": "config/negara-phoneme-id-map.json",
       "sha256": "6e67148a46b9bf5a3529c97cc1fa60a10f477d0bd80e61a1fb1a24ad59eefe83"
     },
+    {
+      "bytes": 63516051,
+      "path": "gooya-rizehpizeh-v2.onnx",
+      "sha256": "675c557524a325cc014e27acb7bb9f7eab584d3247216f934e8a378b709a2d3b"
+    },
+    {
+      "bytes": 5000,
+      "path": "gooya-rizehpizeh-v2.onnx.json",
+      "sha256": "981770210ac1aea618cb8134597127911051deabf9900824df3388f209a884fa"
+    },
     {
       "bytes": 1903,
       "path": "training/alignment-report.json",
@@ -49,5 +69,5 @@
   "schema_version": "gooya.rizehpizeh-v2-release/v1",
   "selected_global_step": 50000,
   "selected_val_mel": 0.3951,
-  "status": "trainable-checkpoint-ready"
+  "status": "checkpoint-and-browser-onnx-ready"
 }