{ "architecture": "Ninada-24k-StyleTTS2-PLBERT-iSTFTNet", "version": "3.0.0", "sample_rate": 24000, "hop_length": 600, "vocab_size": 178, "retroflex_lateral_slot": 79, "fp32_size_mb": 310.46, "q8f16_size_mb": 87.48, "pack_info": { "pipeline": "quant_pre_process + quantize_dynamic(QUInt8)", "size_mb": 87.48, "saved_mb": 222.98 }, "onnx_file": "onnx/ninada_24k_q8f16.onnx", "voices": { "sa": { "file": "voices/sa.bin", "bytes": 522240, "shape": [ 510, 1, 256 ], "l2_norm_mean": 2.9989 }, "hi": { "file": "voices/hi.bin", "bytes": 522240, "shape": [ 510, 1, 256 ], "l2_norm_mean": 2.9725 }, "kn": { "file": "voices/kn.bin", "bytes": 522240, "shape": [ 510, 1, 256 ], "l2_norm_mean": 3.0111 }, "ta": { "file": "voices/ta.bin", "bytes": 522240, "shape": [ 510, 1, 256 ], "l2_norm_mean": 2.9772 }, "te": { "file": "voices/te.bin", "bytes": 522240, "shape": [ 510, 1, 256 ], "l2_norm_mean": 3.0128 }, "ml": { "file": "voices/ml.bin", "bytes": 522240, "shape": [ 510, 1, 256 ], "l2_norm_mean": 3.0242 } }, "probes": { "sa": { "ipa": "dʰˈəɾməkʂeːtɾeː kʊɾˈʊkʂeːtɾeː səməʋˈeːtɑː jʊjˈʊtsəʋəhᵊ ; mˈɑːməkɑːh pˈɑːɳɖəʋɑːɕʧaɪʋə kɪməkˈʊɾʋətə sˈəɲʤəjə .", "num_tokens": 110, "duration_sec": 5.85, "latency_ms": 1815.53, "rtf": 0.3103, "rms": 0.0849, "peak": 0.4988 }, "hi": { "ipa": "nəmˈəsteː, ˈɑːʤ kˈɑː mˈɔːsəm bəhˈʊt ˈəʧʧʰɑː hˈæː ˈɔːɾ hˈəm səbʰˈiː sˈɑːtʰ mɪləkˈəɾ kʰˈʊɕ hˈæː̃.", "num_tokens": 97, "duration_sec": 4.95, "latency_ms": 1479.67, "rtf": 0.2989, "rms": 0.0827, "peak": 0.4658 }, "kn": { "ipa": "nəmˈəskɑːɾə , ˈɪndʊ bˈɛŋɡəɭuːɾɪnəllɪ həʋˈɑːmɑːnə tˈʊmbɑː ʧˈɛnnɑːɡɪdɛ .", "num_tokens": 72, "duration_sec": 3.925, "latency_ms": 1157.28, "rtf": 0.2948, "rms": 0.0932, "peak": 0.5808 }, "ta": { "ipa": "ʋəɳˈəkkəm, ˈɪndɾʊ sˈɛnnəɪjɪl ʋˈɑːnɪləɪ mɪɡəʋˈʊm ɪnɪmˈəɪjɑːɡə ˈʊɭɭəðʊ , nˈəndɾɪ .", "num_tokens": 82, "duration_sec": 4.35, "latency_ms": 1291.13, "rtf": 0.2968, "rms": 0.0887, "peak": 0.4569 }, "te": { "ipa": "nəmˈəskɑːɾəm, ˈiːɾoːʤʊ hˈaɪdəɾɑːbɑːdloː ʋˈɑːtɑːʋəɾəɳəm ʧˈɑːlɑː bˈɑːɡʊndɪ .", "num_tokens": 76, "duration_sec": 4.025, "latency_ms": 1193.07, "rtf": 0.2964, "rms": 0.0908, "peak": 0.6304 }, "ml": { "ipa": "nəmˈəskɑːɾəm, ˈɪnnə kˈeːɾəɭəttɪl ʋˈəɭəɾɛ nˈəllə kˈɑːlɑːʋəstʰəjɑːɳə , nˈəndɪ .", "num_tokens": 79, "duration_sec": 4.2, "latency_ms": 1243.04, "rtf": 0.296, "rms": 0.0933, "peak": 0.4962 } }, "vocab": { ";": 1, ":": 2, ",": 3, ".": 4, "!": 5, "?": 6, "—": 9, "…": 10, "\"": 11, "(": 12, ")": 13, "“": 14, "”": 15, " ": 16, "̃": 17, "ʣ": 18, "ʥ": 19, "ʦ": 20, "ʨ": 21, "ᵝ": 22, "ꭧ": 23, "A": 24, "I": 25, "O": 31, "Q": 33, "S": 35, "T": 36, "W": 39, "Y": 41, "ᵊ": 42, "a": 43, "b": 44, "c": 45, "d": 46, "e": 47, "f": 48, "h": 50, "i": 51, "j": 52, "k": 53, "l": 54, "m": 55, "n": 56, "o": 57, "p": 58, "q": 59, "r": 60, "s": 61, "t": 62, "u": 63, "v": 64, "w": 65, "x": 66, "y": 67, "z": 68, "ɑ": 69, "ɐ": 70, "ɒ": 71, "æ": 72, "β": 75, "ɔ": 76, "ɕ": 77, "ç": 78, "ɭ": 79, "ɖ": 80, "ð": 81, "ʤ": 82, "ə": 83, "ɚ": 85, "ɛ": 86, "ɜ": 87, "ɟ": 90, "ɡ": 92, "ɥ": 99, "ɨ": 101, "ɪ": 102, "ʝ": 103, "ɯ": 110, "ɰ": 111, "ŋ": 112, "ɳ": 113, "ɲ": 114, "ɴ": 115, "ø": 116, "ɸ": 118, "θ": 119, "œ": 120, "ɹ": 123, "ɾ": 125, "ɻ": 126, "ʁ": 128, "ɽ": 129, "ʂ": 130, "ʃ": 131, "ʈ": 132, "ʧ": 133, "ʊ": 135, "ʋ": 136, "ʌ": 138, "ɣ": 139, "ɤ": 140, "χ": 142, "ʎ": 143, "ʒ": 147, "ʔ": 148, "ˈ": 156, "ˌ": 157, "ː": 158, "ʰ": 162, "ʲ": 164, "↓": 169, "→": 171, "↗": 172, "↘": 173, "ᵻ": 177 } }