Upload 2 files

Hey! I’ve been working on another fine-tune of my Czech Piper voice, Kasandra.

This version focuses much more on natural prosody, emotional delivery, emphasis, and sentence endings. The biggest improvement isn’t really noticeable in short neutral sentences, but in longer speech.

What surprised me is that she can now reproduce the emotional delivery from the training recordings surprisingly well. Honestly, there are some lines where I don’t think I could read them with the same emotional expression myself. 😄

It’s getting pretty close to an ElevenLabs-style voice, but running locally with Piper.

cs/cs_CZ/kasandra/medium/cs_CZ-kasandra_v3.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:752e6a3e3d69f63911ba9565999ae6a6ccee64de29e0c0ce6b59206b0476f35a
+size 63511038

cs/cs_CZ/kasandra/medium/cs_CZ-kasandra_v3.onnx.json

@@ -0,0 +1,503 @@
+{
+    "dataset": "cs_CZ-kasandra_v3",
+    "audio": {
+        "sample_rate": 22050,
+        "quality": "kasandra_verze_3"
+    },
+    "espeak": {
+        "voice": "cs"
+    },
+    "language": {
+        "code": "cs"
+    },
+    "inference": {
+        "noise_scale": 0.567,
+        "length_scale": 1.22,
+        "noise_w": 1.1
+    },
+    "phoneme_type": "espeak",
+    "phoneme_map": {},
+    "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
+        ],
+        "?": [
+            13
+        ],
+        "X": [
+            156
+        ],
+        "^": [
+            1
+        ],
+        "_": [
+            0
+        ],
+        "a": [
+            14
+        ],
+        "b": [
+            15
+        ],
+        "c": [
+            16
+        ],
+        "d": [
+            17
+        ],
+        "e": [
+            18
+        ],
+        "f": [
+            19
+        ],
+        "g": [
+            154
+        ],
+        "h": [
+            20
+        ],
+        "i": [
+            21
+        ],
+        "j": [
+            22
+        ],
+        "k": [
+            23
+        ],
+        "l": [
+            24
+        ],
+        "m": [
+            25
+        ],
+        "n": [
+            26
+        ],
+        "o": [
+            27
+        ],
+        "p": [
+            28
+        ],
+        "q": [
+            29
+        ],
+        "r": [
+            30
+        ],
+        "s": [
+            31
+        ],
+        "t": [
+            32
+        ],
+        "u": [
+            33
+        ],
+        "v": [
+            34
+        ],
+        "w": [
+            35
+        ],
+        "x": [
+            36
+        ],
+        "y": [
+            37
+        ],
+        "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
+        ],
+        "̊": [
+            158
+        ],
+        "̝": [
+            157
+        ],
+        "̧": [
+            140
+        ],
+        "̩": [
+            144
+        ],
+        "̪": [
+            142
+        ],
+        "̯": [
+            143
+        ],
+        "̺": [
+            152
+        ],
+        "̻": [
+            153
+        ],
+        "β": [
+            125
+        ],
+        "ε": [
+            147
+        ],
+        "θ": [
+            126
+        ],
+        "χ": [
+            127
+        ],
+        "ᵻ": [
+            128
+        ],
+        "↑": [
+            151
+        ],
+        "↓": [
+            148
+        ],
+        "ⱱ": [
+            129
+        ]
+    },
+    "num_symbols": 256,
+    "num_speakers": 1,
+    "speaker_id_map": {},
+    "piper_version": "1.0.0"
+}