Chatterbox TTS (kn)

kn/chatterbox-kannada-tts/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

kn/chatterbox-kannada-tts/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 4.03440523147583,
+    "eval_runtime": 57.5417,
+    "eval_samples_per_second": 3.319,
+    "eval_steps_per_second": 0.417,
+    "total_flos": 0.0,
+    "train_loss": 4.406593790995717,
+    "train_runtime": 4471.1894,
+    "train_samples_per_second": 2.084,
+    "train_steps_per_second": 0.261
+}

kn/chatterbox-kannada-tts/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 4.03440523147583,
+    "eval_runtime": 57.5417,
+    "eval_samples_per_second": 3.319,
+    "eval_steps_per_second": 0.417
+}

kn/chatterbox-kannada-tts/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0510b885ff31f0e23a191274e7171b7203146e3e3e6a35be7a77e450f0fddd9b
+size 2129654648

kn/chatterbox-kannada-tts/s3gen.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b78103c654207393955e4900aac14a12de8ef25f4b09424f1ef91941f161d4e
+size 1056484620

kn/chatterbox-kannada-tts/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/Karthikappi0011/chatterbox-kannada-tts

kn/chatterbox-kannada-tts/t3_cfg.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c97f1afae711b8d23dc3cd07a7081c566b9f0df5e3ca7325dd4eb124bac552f0
+size 2129653744

kn/chatterbox-kannada-tts/tokenizer.json

@@ -0,0 +1,1435 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "special": true,
+      "content": "[STOP]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 1,
+      "special": true,
+      "content": "[UNK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 2,
+      "special": true,
+      "content": "[SPACE]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 255,
+      "special": true,
+      "content": "[START]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 604,
+      "content": "[UH]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 605,
+      "content": "[UM]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 606,
+      "content": "[giggle]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 607,
+      "content": "[laughter]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 608,
+      "content": "[guffaw]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 609,
+      "content": "[inhale]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 610,
+      "content": "[exhale]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 611,
+      "content": "[sigh]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 612,
+      "content": "[cry]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 613,
+      "content": "[bark]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 614,
+      "content": "[howl]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 615,
+      "content": "[meow]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 616,
+      "content": "[singing]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 617,
+      "content": "[music]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 618,
+      "content": "[whistle]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 619,
+      "content": "[humming]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 620,
+      "content": "[gasp]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 621,
+      "content": "[groan]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 622,
+      "content": "[whisper]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 623,
+      "content": "[mumble]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 624,
+      "content": "[sniff]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 625,
+      "content": "[sneeze]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 626,
+      "content": "[cough]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 627,
+      "content": "[snore]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 628,
+      "content": "[chew]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 629,
+      "content": "[sip]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 630,
+      "content": "[clear_throat]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 631,
+      "content": "[kiss]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 632,
+      "content": "[shhh]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 633,
+      "content": "[gibberish]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 634,
+      "content": "[fr]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 635,
+      "content": "[es]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 636,
+      "content": "[de]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 637,
+      "content": "[it]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 638,
+      "content": "[ipa]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 639,
+      "content": "[end_of_label]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 695,
+      "content": "[PLACEHOLDER55]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 696,
+      "content": "[PLACEHOLDER56]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 697,
+      "content": "[PLACEHOLDER57]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 698,
+      "content": "[PLACEHOLDER58]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 699,
+      "content": "[PLACEHOLDER59]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 700,
+      "content": "[PLACEHOLDER60]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 701,
+      "content": "[PLACEHOLDER61]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 702,
+      "content": "[PLACEHOLDER62]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 703,
+      "content": "[PLACEHOLDER63]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "[UNK]",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "vocab": {
+      "[STOP]": 0,
+      "[UNK]": 1,
+      "[SPACE]": 2,
+      "!": 3,
+      "'": 4,
+      "(": 5,
+      ")": 6,
+      ",": 7,
+      "-": 8,
+      ".": 9,
+      "/": 10,
+      ":": 11,
+      ";": 12,
+      "?": 13,
+      "a": 14,
+      "b": 15,
+      "c": 16,
+      "d": 17,
+      "e": 18,
+      "f": 19,
+      "g": 20,
+      "h": 21,
+      "i": 22,
+      "j": 23,
+      "k": 24,
+      "l": 25,
+      "m": 26,
+      "n": 27,
+      "o": 28,
+      "p": 29,
+      "q": 30,
+      "r": 31,
+      "s": 32,
+      "t": 33,
+      "u": 34,
+      "v": 35,
+      "w": 36,
+      "x": 37,
+      "y": 38,
+      "z": 39,
+      "th": 40,
+      "in": 41,
+      "the": 42,
+      "an": 43,
+      "er": 44,
+      "ou": 45,
+      "re": 46,
+      "on": 47,
+      "at": 48,
+      "ed": 49,
+      "en": 50,
+      "to": 51,
+      "ing": 52,
+      "and": 53,
+      "is": 54,
+      "as": 55,
+      "al": 56,
+      "or": 57,
+      "of": 58,
+      "ar": 59,
+      "it": 60,
+      "es": 61,
+      "he": 62,
+      "st": 63,
+      "le": 64,
+      "om": 65,
+      "se": 66,
+      "be": 67,
+      "ad": 68,
+      "ow": 69,
+      "ly": 70,
+      "ch": 71,
+      "wh": 72,
+      "that": 73,
+      "you": 74,
+      "li": 75,
+      "ve": 76,
+      "ac": 77,
+      "ti": 78,
+      "ld": 79,
+      "me": 80,
+      "was": 81,
+      "gh": 82,
+      "id": 83,
+      "ll": 84,
+      "wi": 85,
+      "ent": 86,
+      "for": 87,
+      "ay": 88,
+      "ro": 89,
+      "ver": 90,
+      "ic": 91,
+      "her": 92,
+      "ke": 93,
+      "his": 94,
+      "no": 95,
+      "ut": 96,
+      "un": 97,
+      "ir": 98,
+      "lo": 99,
+      "we": 100,
+      "ri": 101,
+      "ha": 102,
+      "with": 103,
+      "ght": 104,
+      "out": 105,
+      "im": 106,
+      "ion": 107,
+      "all": 108,
+      "ab": 109,
+      "one": 110,
+      "ne": 111,
+      "ge": 112,
+      "ould": 113,
+      "ter": 114,
+      "mo": 115,
+      "had": 116,
+      "ce": 117,
+      "she": 118,
+      "go": 119,
+      "sh": 120,
+      "ur": 121,
+      "am": 122,
+      "so": 123,
+      "pe": 124,
+      "my": 125,
+      "de": 126,
+      "are": 127,
+      "but": 128,
+      "ome": 129,
+      "fr": 130,
+      "ther": 131,
+      "fe": 132,
+      "su": 133,
+      "do": 134,
+      "con": 135,
+      "te": 136,
+      "ain": 137,
+      "ere": 138,
+      "po": 139,
+      "if": 140,
+      "they": 141,
+      "us": 142,
+      "ag": 143,
+      "tr": 144,
+      "now": 145,
+      "oun": 146,
+      "this": 147,
+      "have": 148,
+      "not": 149,
+      "sa": 150,
+      "il": 151,
+      "up": 152,
+      "thing": 153,
+      "from": 154,
+      "ap": 155,
+      "him": 156,
+      "ack": 157,
+      "ation": 158,
+      "ant": 159,
+      "our": 160,
+      "op": 161,
+      "like": 162,
+      "ust": 163,
+      "ess": 164,
+      "bo": 165,
+      "ok": 166,
+      "ul": 167,
+      "ind": 168,
+      "ex": 169,
+      "com": 170,
+      "some": 171,
+      "there": 172,
+      "ers": 173,
+      "co": 174,
+      "res": 175,
+      "man": 176,
+      "ard": 177,
+      "pl": 178,
+      "wor": 179,
+      "way": 180,
+      "tion": 181,
+      "fo": 182,
+      "ca": 183,
+      "were": 184,
+      "by": 185,
+      "ate": 186,
+      "pro": 187,
+      "ted": 188,
+      "ound": 189,
+      "own": 190,
+      "would": 191,
+      "ts": 192,
+      "what": 193,
+      "qu": 194,
+      "ally": 195,
+      "ight": 196,
+      "ck": 197,
+      "gr": 198,
+      "when": 199,
+      "ven": 200,
+      "can": 201,
+      "ough": 202,
+      "ine": 203,
+      "end": 204,
+      "per": 205,
+      "ous": 206,
+      "od": 207,
+      "ide": 208,
+      "know": 209,
+      "ty": 210,
+      "very": 211,
+      "si": 212,
+      "ak": 213,
+      "who": 214,
+      "about": 215,
+      "ill": 216,
+      "them": 217,
+      "est": 218,
+      "red": 219,
+      "ye": 220,
+      "could": 221,
+      "ong": 222,
+      "your": 223,
+      "their": 224,
+      "em": 225,
+      "just": 226,
+      "other": 227,
+      "into": 228,
+      "any": 229,
+      "whi": 230,
+      "um": 231,
+      "tw": 232,
+      "ast": 233,
+      "der": 234,
+      "did": 235,
+      "ie": 236,
+      "been": 237,
+      "ace": 238,
+      "ink": 239,
+      "ity": 240,
+      "back": 241,
+      "ting": 242,
+      "br": 243,
+      "more": 244,
+      "ake": 245,
+      "pp": 246,
+      "then": 247,
+      "sp": 248,
+      "el": 249,
+      "use": 250,
+      "bl": 251,
+      "said": 252,
+      "over": 253,
+      "get": 254,
+      "[START]": 255,
+      "\"": 256,
+      "#": 257,
+      "$": 258,
+      "%": 259,
+      "&": 260,
+      "*": 261,
+      "+": 262,
+      "0": 263,
+      "1": 264,
+      "2": 265,
+      "3": 266,
+      "4": 267,
+      "5": 268,
+      "6": 269,
+      "7": 270,
+      "8": 271,
+      "9": 272,
+      "<": 273,
+      "=": 274,
+      ">": 275,
+      "@": 276,
+      "A": 277,
+      "B": 278,
+      "C": 279,
+      "D": 280,
+      "E": 281,
+      "F": 282,
+      "G": 283,
+      "H": 284,
+      "I": 285,
+      "J": 286,
+      "K": 287,
+      "L": 288,
+      "M": 289,
+      "N": 290,
+      "O": 291,
+      "P": 292,
+      "Q": 293,
+      "R": 294,
+      "S": 295,
+      "T": 296,
+      "U": 297,
+      "V": 298,
+      "W": 299,
+      "X": 300,
+      "Y": 301,
+      "Z": 302,
+      "[": 303,
+      "\\": 304,
+      "]": 305,
+      "^": 306,
+      "_": 307,
+      "`": 308,
+      "{": 309,
+      "|": 310,
+      "}": 311,
+      "~": 312,
+      "‐": 313,
+      "‑": 314,
+      "‒": 315,
+      "–": 316,
+      "—": 317,
+      "―": 318,
+      "‖": 319,
+      "‗": 320,
+      "‘": 321,
+      "’": 322,
+      "‚": 323,
+      "‛": 324,
+      "“": 325,
+      "”": 326,
+      "„": 327,
+      "‟": 328,
+      " ": 329,
+      "¡": 330,
+      "¢": 331,
+      "£": 332,
+      "¤": 333,
+      "¥": 334,
+      "¦": 335,
+      "§": 336,
+      "¨": 337,
+      "©": 338,
+      "ª": 339,
+      "«": 340,
+      "¬": 341,
+      "­": 342,
+      "®": 343,
+      "¯": 344,
+      "°": 345,
+      "±": 346,
+      "²": 347,
+      "³": 348,
+      "´": 349,
+      "µ": 350,
+      "¶": 351,
+      "·": 352,
+      "¸": 353,
+      "¹": 354,
+      "º": 355,
+      "»": 356,
+      "¼": 357,
+      "½": 358,
+      "¾": 359,
+      "¿": 360,
+      "À": 361,
+      "Á": 362,
+      "Â": 363,
+      "Ã": 364,
+      "Ä": 365,
+      "Å": 366,
+      "Æ": 367,
+      "Ç": 368,
+      "È": 369,
+      "É": 370,
+      "Ê": 371,
+      "Ë": 372,
+      "Ì": 373,
+      "Í": 374,
+      "Î": 375,
+      "Ï": 376,
+      "Ð": 377,
+      "Ñ": 378,
+      "Ò": 379,
+      "Ó": 380,
+      "Ô": 381,
+      "Õ": 382,
+      "Ö": 383,
+      "×": 384,
+      "Ø": 385,
+      "Ù": 386,
+      "Ú": 387,
+      "Û": 388,
+      "Ü": 389,
+      "Ý": 390,
+      "Þ": 391,
+      "ß": 392,
+      "à": 393,
+      "á": 394,
+      "â": 395,
+      "ã": 396,
+      "ä": 397,
+      "å": 398,
+      "æ": 399,
+      "ç": 400,
+      "è": 401,
+      "é": 402,
+      "ê": 403,
+      "ë": 404,
+      "ì": 405,
+      "í": 406,
+      "î": 407,
+      "ï": 408,
+      "ð": 409,
+      "ñ": 410,
+      "ò": 411,
+      "ó": 412,
+      "ô": 413,
+      "õ": 414,
+      "ö": 415,
+      "÷": 416,
+      "ø": 417,
+      "ù": 418,
+      "ú": 419,
+      "û": 420,
+      "ü": 421,
+      "ý": 422,
+      "þ": 423,
+      "ÿ": 424,
+      "ɐ": 425,
+      "ɑ": 426,
+      "ɒ": 427,
+      "ɓ": 428,
+      "ɔ": 429,
+      "ɕ": 430,
+      "ɖ": 431,
+      "ɗ": 432,
+      "ɘ": 433,
+      "ə": 434,
+      "ɚ": 435,
+      "ɛ": 436,
+      "ɜ": 437,
+      "ɝ": 438,
+      "ɞ": 439,
+      "ɟ": 440,
+      "ɠ": 441,
+      "ɡ": 442,
+      "ɢ": 443,
+      "ɣ": 444,
+      "ɤ": 445,
+      "ɥ": 446,
+      "ɦ": 447,
+      "ɧ": 448,
+      "ɨ": 449,
+      "ɩ": 450,
+      "ɪ": 451,
+      "ɫ": 452,
+      "ɬ": 453,
+      "ɭ": 454,
+      "ɮ": 455,
+      "ɯ": 456,
+      "ɰ": 457,
+      "ɱ": 458,
+      "ɲ": 459,
+      "ɳ": 460,
+      "ɴ": 461,
+      "ɵ": 462,
+      "ɶ": 463,
+      "ɷ": 464,
+      "ɸ": 465,
+      "ɹ": 466,
+      "ɺ": 467,
+      "ɻ": 468,
+      "ɼ": 469,
+      "ɽ": 470,
+      "ɾ": 471,
+      "ɿ": 472,
+      "ʀ": 473,
+      "ʁ": 474,
+      "ʂ": 475,
+      "ʃ": 476,
+      "ʄ": 477,
+      "ʅ": 478,
+      "ʆ": 479,
+      "ʇ": 480,
+      "ʈ": 481,
+      "ʉ": 482,
+      "ʊ": 483,
+      "ʋ": 484,
+      "ʌ": 485,
+      "ʍ": 486,
+      "ʎ": 487,
+      "ʏ": 488,
+      "ʐ": 489,
+      "ʑ": 490,
+      "ʒ": 491,
+      "ʓ": 492,
+      "ʔ": 493,
+      "ʕ": 494,
+      "ʖ": 495,
+      "ʗ": 496,
+      "ʘ": 497,
+      "ʙ": 498,
+      "ʚ": 499,
+      "ʛ": 500,
+      "ʜ": 501,
+      "ʝ": 502,
+      "ʞ": 503,
+      "ʟ": 504,
+      "ʠ": 505,
+      "ʡ": 506,
+      "ʢ": 507,
+      "ʣ": 508,
+      "ʤ": 509,
+      "ʥ": 510,
+      "ʦ": 511,
+      "ʧ": 512,
+      "ʨ": 513,
+      "ʩ": 514,
+      "ʪ": 515,
+      "ʫ": 516,
+      "ʬ": 517,
+      "ʭ": 518,
+      "ʮ": 519,
+      "ʯ": 520,
+      "ʰ": 521,
+      "ʱ": 522,
+      "ʲ": 523,
+      "ʳ": 524,
+      "ʴ": 525,
+      "ʵ": 526,
+      "ʶ": 527,
+      "ʷ": 528,
+      "ʸ": 529,
+      "ʹ": 530,
+      "ʺ": 531,
+      "ʻ": 532,
+      "ʼ": 533,
+      "ʽ": 534,
+      "ʾ": 535,
+      "ʿ": 536,
+      "ˀ": 537,
+      "ˁ": 538,
+      "˂": 539,
+      "˃": 540,
+      "˄": 541,
+      "˅": 542,
+      "ˆ": 543,
+      "ˇ": 544,
+      "ˈ": 545,
+      "ˉ": 546,
+      "ˊ": 547,
+      "ˋ": 548,
+      "ˌ": 549,
+      "ˍ": 550,
+      "ˎ": 551,
+      "ˏ": 552,
+      "ː": 553,
+      "ˑ": 554,
+      "˒": 555,
+      "˓": 556,
+      "˔": 557,
+      "˕": 558,
+      "˖": 559,
+      "˗": 560,
+      "˘": 561,
+      "˙": 562,
+      "˚": 563,
+      "˛": 564,
+      "˜": 565,
+      "˝": 566,
+      "˞": 567,
+      "˟": 568,
+      "ˠ": 569,
+      "ˡ": 570,
+      "ˢ": 571,
+      "ˣ": 572,
+      "ˤ": 573,
+      "˥": 574,
+      "˦": 575,
+      "˧": 576,
+      "˨": 577,
+      "˩": 578,
+      "˪": 579,
+      "˫": 580,
+      "ˬ": 581,
+      "˭": 582,
+      "ˮ": 583,
+      "˯": 584,
+      "˰": 585,
+      "˱": 586,
+      "˲": 587,
+      "˳": 588,
+      "˴": 589,
+      "˵": 590,
+      "˶": 591,
+      "˷": 592,
+      "˸": 593,
+      "˹": 594,
+      "˺": 595,
+      "˻": 596,
+      "˼": 597,
+      "˽": 598,
+      "˾": 599,
+      "˿": 600,
+      "ā": 601,
+      "ō": 602,
+      "…": 603,
+      "[UH]": 604,
+      "[UM]": 605,
+      "[giggle]": 606,
+      "[laughter]": 607,
+      "[guffaw]": 608,
+      "[inhale]": 609,
+      "[exhale]": 610,
+      "[sigh]": 611,
+      "[cry]": 612,
+      "[bark]": 613,
+      "[howl]": 614,
+      "[meow]": 615,
+      "[singing]": 616,
+      "[music]": 617,
+      "[whistle]": 618,
+      "[humming]": 619,
+      "[gasp]": 620,
+      "[groan]": 621,
+      "[whisper]": 622,
+      "[mumble]": 623,
+      "[sniff]": 624,
+      "[sneeze]": 625,
+      "[cough]": 626,
+      "[snore]": 627,
+      "[chew]": 628,
+      "[sip]": 629,
+      "[clear_throat]": 630,
+      "[kiss]": 631,
+      "[shhh]": 632,
+      "[gibberish]": 633,
+      "[fr]": 634,
+      "[es]": 635,
+      "[de]": 636,
+      "[it]": 637,
+      "[ipa]": 638,
+      "[end_of_label]": 639,
+      "ŋ": 640,
+      "ᵻ": 641,
+      "θ": 642,
+      "̩": 643,
+      "\u0303": 644,
+      "ɑː": 645,
+      "iː": 646,
+      "uː": 647,
+      "ɜː": 648,
+      "ɔː": 649,
+      "oː": 650,
+      "eɪ": 651,
+      "oʊ": 652,
+      "aɪ": 653,
+      "aʊ": 654,
+      "ɔɪ": 655,
+      "dʒ": 656,
+      "tʃ": 657,
+      "ɪŋ": 658,
+      "ᵻd": 659,
+      "ˈiː": 660,
+      "ˌiː": 661,
+      "ˈɪ": 662,
+      "ˌɪ": 663,
+      "ˈeɪ": 664,
+      "ˌeɪ": 665,
+      "ˈɛ": 666,
+      "ˌɛ": 667,
+      "ˈæ": 668,
+      "ˌæ": 669,
+      "ˈɑː": 670,
+      "ˌɑː": 671,
+      "ˈɔː": 672,
+      "ˌɔː": 673,
+      "oːɹ": 674,
+      "ˈoːɹ": 675,
+      "ˌoːɹ": 676,
+      "ˈoʊ": 677,
+      "ˌoʊ": 678,
+      "ˈʊ": 679,
+      "ˌʊ": 680,
+      "ˈuː": 681,
+      "ˌuː": 682,
+      "ˈɜː": 683,
+      "ˌɜː": 684,
+      "ˈʌ": 685,
+      "ˌʌ": 686,
+      "ˈaɪ": 687,
+      "ˌaɪ": 688,
+      "ˈaʊ": 689,
+      "ˌaʊ": 690,
+      "ˈɔɪ": 691,
+      "ˌɔɪ": 692,
+      "ˈɚ": 693,
+      "ˌɐ": 694,
+      "[PLACEHOLDER55]": 695,
+      "[PLACEHOLDER56]": 696,
+      "[PLACEHOLDER57]": 697,
+      "[PLACEHOLDER58]": 698,
+      "[PLACEHOLDER59]": 699,
+      "[PLACEHOLDER60]": 700,
+      "[PLACEHOLDER61]": 701,
+      "[PLACEHOLDER62]": 702,
+      "[PLACEHOLDER63]": 703
+    },
+    "merges": [
+      "t h",
+      "i n",
+      "th e",
+      "a n",
+      "e r",
+      "o u",
+      "r e",
+      "o n",
+      "a t",
+      "e d",
+      "e n",
+      "t o",
+      "in g",
+      "an d",
+      "i s",
+      "a s",
+      "a l",
+      "o r",
+      "o f",
+      "a r",
+      "i t",
+      "e s",
+      "h e",
+      "s t",
+      "l e",
+      "o m",
+      "s e",
+      "b e",
+      "a d",
+      "o w",
+      "l y",
+      "c h",
+      "w h",
+      "th at",
+      "y ou",
+      "l i",
+      "v e",
+      "a c",
+      "t i",
+      "l d",
+      "m e",
+      "w as",
+      "g h",
+      "i d",
+      "l l",
+      "w i",
+      "en t",
+      "f or",
+      "a y",
+      "r o",
+      "v er",
+      "i c",
+      "h er",
+      "k e",
+      "h is",
+      "n o",
+      "u t",
+      "u n",
+      "i r",
+      "l o",
+      "w e",
+      "r i",
+      "h a",
+      "wi th",
+      "gh t",
+      "ou t",
+      "i m",
+      "i on",
+      "al l",
+      "a b",
+      "on e",
+      "n e",
+      "g e",
+      "ou ld",
+      "t er",
+      "m o",
+      "h ad",
+      "c e",
+      "s he",
+      "g o",
+      "s h",
+      "u r",
+      "a m",
+      "s o",
+      "p e",
+      "m y",
+      "d e",
+      "a re",
+      "b ut",
+      "om e",
+      "f r",
+      "the r",
+      "f e",
+      "s u",
+      "d o",
+      "c on",
+      "t e",
+      "a in",
+      "er e",
+      "p o",
+      "i f",
+      "the y",
+      "u s",
+      "a g",
+      "t r",
+      "n ow",
+      "ou n",
+      "th is",
+      "ha ve",
+      "no t",
+      "s a",
+      "i l",
+      "u p",
+      "th ing",
+      "fr om",
+      "a p",
+      "h im",
+      "ac k",
+      "at ion",
+      "an t",
+      "ou r",
+      "o p",
+      "li ke",
+      "u st",
+      "es s",
+      "b o",
+      "o k",
+      "u l",
+      "in d",
+      "e x",
+      "c om",
+      "s ome",
+      "the re",
+      "er s",
+      "c o",
+      "re s",
+      "m an",
+      "ar d",
+      "p l",
+      "w or",
+      "w ay",
+      "ti on",
+      "f o",
+      "c a",
+      "w ere",
+      "b y",
+      "at e",
+      "p ro",
+      "t ed",
+      "oun d",
+      "ow n",
+      "w ould",
+      "t s",
+      "wh at",
+      "q u",
+      "al ly",
+      "i ght",
+      "c k",
+      "g r",
+      "wh en",
+      "v en",
+      "c an",
+      "ou gh",
+      "in e",
+      "en d",
+      "p er",
+      "ou s",
+      "o d",
+      "id e",
+      "k now",
+      "t y",
+      "ver y",
+      "s i",
+      "a k",
+      "wh o",
+      "ab out",
+      "i ll",
+      "the m",
+      "es t",
+      "re d",
+      "y e",
+      "c ould",
+      "on g",
+      "you r",
+      "the ir",
+      "e m",
+      "j ust",
+      "o ther",
+      "in to",
+      "an y",
+      "wh i",
+      "u m",
+      "t w",
+      "as t",
+      "d er",
+      "d id",
+      "i e",
+      "be en",
+      "ac e",
+      "in k",
+      "it y",
+      "b ack",
+      "t ing",
+      "b r",
+      "mo re",
+      "a ke",
+      "p p",
+      "the n",
+      "s p",
+      "e l",
+      "u se",
+      "b l",
+      "sa id",
+      "o ver",
+      "ge t",
+      "ɑ ː",
+      "i ː",
+      "u ː",
+      "ɜ ː",
+      "ɔ ː",
+      "o ː",
+      "e ɪ",
+      "o ʊ",
+      "a ɪ",
+      "a ʊ",
+      "ɔ ɪ",
+      "d ʒ",
+      "t ʃ",
+      "ɪ ŋ",
+      "ᵻ d",
+      "ˈ iː",
+      "ˌ iː",
+      "ˈ ɪ",
+      "ˌ ɪ",
+      "ˈ eɪ",
+      "ˌ eɪ",
+      "ˈ ɛ",
+      "ˌ ɛ",
+      "ˈ æ",
+      "ˌ æ",
+      "ˈ ɑː",
+      "ˌ ɑː",
+      "ˈ ɔː",
+      "ˌ ɔː",
+      "oː ɹ",
+      "ˈ oːɹ",
+      "ˌ oːɹ",
+      "ˈ oʊ",
+      "ˌ oʊ",
+      "ˈ ʊ",
+      "ˌ ʊ",
+      "ˈ uː",
+      "ˌ uː",
+      "ˈ ɜː",
+      "ˌ ɜː",
+      "ˈ ʌ",
+      "ˌ ʌ",
+      "ˈ aɪ",
+      "ˌ aɪ",
+      "ˈ aʊ",
+      "ˌ aʊ",
+      "ˈ ɔɪ",
+      "ˌ ɔɪ",
+      "ˈ ɚ",
+      "ˌ ɐ"
+    ]
+  }
+}

kn/chatterbox-kannada-tts/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 4.406593790995717,
+    "train_runtime": 4471.1894,
+    "train_samples_per_second": 2.084,
+    "train_steps_per_second": 0.261
+}

kn/chatterbox-kannada-tts/trainer_state.json

@@ -0,0 +1,1047 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 1165,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 18.01746368408203,
+      "eval_runtime": 55.9577,
+      "eval_samples_per_second": 3.413,
+      "eval_steps_per_second": 0.429,
+      "step": 0
+    },
+    {
+      "epoch": 0.008587376556462,
+      "grad_norm": 234.4429473876953,
+      "learning_rate": 2.5e-06,
+      "loss": 17.6251,
+      "step": 10
+    },
+    {
+      "epoch": 0.017174753112924,
+      "grad_norm": 13.365180969238281,
+      "learning_rate": 7.5e-06,
+      "loss": 6.9383,
+      "step": 20
+    },
+    {
+      "epoch": 0.025762129669386003,
+      "grad_norm": 17.381061553955078,
+      "learning_rate": 1.25e-05,
+      "loss": 5.3568,
+      "step": 30
+    },
+    {
+      "epoch": 0.034349506225848,
+      "grad_norm": 10.483255386352539,
+      "learning_rate": 1.75e-05,
+      "loss": 4.8448,
+      "step": 40
+    },
+    {
+      "epoch": 0.042936882782310004,
+      "grad_norm": 4.615546226501465,
+      "learning_rate": 2.25e-05,
+      "loss": 4.8335,
+      "step": 50
+    },
+    {
+      "epoch": 0.042936882782310004,
+      "eval_loss": 4.86939001083374,
+      "eval_runtime": 66.855,
+      "eval_samples_per_second": 2.857,
+      "eval_steps_per_second": 0.359,
+      "step": 50
+    },
+    {
+      "epoch": 0.051524259338772006,
+      "grad_norm": 14.122917175292969,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 4.9081,
+      "step": 60
+    },
+    {
+      "epoch": 0.06011163589523401,
+      "grad_norm": 6.2480292320251465,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 4.5583,
+      "step": 70
+    },
+    {
+      "epoch": 0.068699012451696,
+      "grad_norm": 5.986227989196777,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 4.8435,
+      "step": 80
+    },
+    {
+      "epoch": 0.07728638900815801,
+      "grad_norm": 11.907475471496582,
+      "learning_rate": 4.25e-05,
+      "loss": 4.5991,
+      "step": 90
+    },
+    {
+      "epoch": 0.08587376556462001,
+      "grad_norm": 6.103641033172607,
+      "learning_rate": 4.75e-05,
+      "loss": 4.8082,
+      "step": 100
+    },
+    {
+      "epoch": 0.08587376556462001,
+      "eval_loss": 4.776334762573242,
+      "eval_runtime": 65.0731,
+      "eval_samples_per_second": 2.935,
+      "eval_steps_per_second": 0.369,
+      "step": 100
+    },
+    {
+      "epoch": 0.094461142121082,
+      "grad_norm": 8.854158401489258,
+      "learning_rate": 4.976525821596245e-05,
+      "loss": 4.7095,
+      "step": 110
+    },
+    {
+      "epoch": 0.10304851867754401,
+      "grad_norm": 8.236750602722168,
+      "learning_rate": 4.929577464788733e-05,
+      "loss": 4.9007,
+      "step": 120
+    },
+    {
+      "epoch": 0.11163589523400601,
+      "grad_norm": 5.69953727722168,
+      "learning_rate": 4.882629107981221e-05,
+      "loss": 4.6707,
+      "step": 130
+    },
+    {
+      "epoch": 0.12022327179046802,
+      "grad_norm": 5.180475234985352,
+      "learning_rate": 4.835680751173709e-05,
+      "loss": 4.6298,
+      "step": 140
+    },
+    {
+      "epoch": 0.12881064834693,
+      "grad_norm": 4.9319329261779785,
+      "learning_rate": 4.788732394366197e-05,
+      "loss": 4.4715,
+      "step": 150
+    },
+    {
+      "epoch": 0.12881064834693,
+      "eval_loss": 4.671267986297607,
+      "eval_runtime": 62.2969,
+      "eval_samples_per_second": 3.066,
+      "eval_steps_per_second": 0.385,
+      "step": 150
+    },
+    {
+      "epoch": 0.137398024903392,
+      "grad_norm": 2.6472439765930176,
+      "learning_rate": 4.741784037558686e-05,
+      "loss": 4.6412,
+      "step": 160
+    },
+    {
+      "epoch": 0.145985401459854,
+      "grad_norm": 5.548781871795654,
+      "learning_rate": 4.694835680751174e-05,
+      "loss": 4.5592,
+      "step": 170
+    },
+    {
+      "epoch": 0.15457277801631603,
+      "grad_norm": 3.5728821754455566,
+      "learning_rate": 4.647887323943662e-05,
+      "loss": 4.6355,
+      "step": 180
+    },
+    {
+      "epoch": 0.16316015457277802,
+      "grad_norm": 6.466938018798828,
+      "learning_rate": 4.60093896713615e-05,
+      "loss": 4.8681,
+      "step": 190
+    },
+    {
+      "epoch": 0.17174753112924002,
+      "grad_norm": 5.174717426300049,
+      "learning_rate": 4.553990610328639e-05,
+      "loss": 4.6163,
+      "step": 200
+    },
+    {
+      "epoch": 0.17174753112924002,
+      "eval_loss": 4.536721229553223,
+      "eval_runtime": 66.3149,
+      "eval_samples_per_second": 2.88,
+      "eval_steps_per_second": 0.362,
+      "step": 200
+    },
+    {
+      "epoch": 0.180334907685702,
+      "grad_norm": 3.7127885818481445,
+      "learning_rate": 4.507042253521127e-05,
+      "loss": 4.2484,
+      "step": 210
+    },
+    {
+      "epoch": 0.188922284242164,
+      "grad_norm": 5.023091793060303,
+      "learning_rate": 4.4600938967136154e-05,
+      "loss": 4.5084,
+      "step": 220
+    },
+    {
+      "epoch": 0.19750966079862603,
+      "grad_norm": 3.8958029747009277,
+      "learning_rate": 4.413145539906103e-05,
+      "loss": 4.4673,
+      "step": 230
+    },
+    {
+      "epoch": 0.20609703735508803,
+      "grad_norm": 4.378758430480957,
+      "learning_rate": 4.366197183098591e-05,
+      "loss": 4.6406,
+      "step": 240
+    },
+    {
+      "epoch": 0.21468441391155002,
+      "grad_norm": 4.872523784637451,
+      "learning_rate": 4.3192488262910805e-05,
+      "loss": 4.2655,
+      "step": 250
+    },
+    {
+      "epoch": 0.21468441391155002,
+      "eval_loss": 4.493251800537109,
+      "eval_runtime": 57.7685,
+      "eval_samples_per_second": 3.306,
+      "eval_steps_per_second": 0.415,
+      "step": 250
+    },
+    {
+      "epoch": 0.22327179046801202,
+      "grad_norm": 5.894066333770752,
+      "learning_rate": 4.2723004694835684e-05,
+      "loss": 4.4658,
+      "step": 260
+    },
+    {
+      "epoch": 0.231859167024474,
+      "grad_norm": 3.809468984603882,
+      "learning_rate": 4.225352112676056e-05,
+      "loss": 4.2519,
+      "step": 270
+    },
+    {
+      "epoch": 0.24044654358093603,
+      "grad_norm": 9.010083198547363,
+      "learning_rate": 4.178403755868545e-05,
+      "loss": 4.4049,
+      "step": 280
+    },
+    {
+      "epoch": 0.24903392013739803,
+      "grad_norm": 3.8174712657928467,
+      "learning_rate": 4.1314553990610335e-05,
+      "loss": 4.1648,
+      "step": 290
+    },
+    {
+      "epoch": 0.25762129669386,
+      "grad_norm": 4.369571208953857,
+      "learning_rate": 4.0845070422535214e-05,
+      "loss": 4.4186,
+      "step": 300
+    },
+    {
+      "epoch": 0.25762129669386,
+      "eval_loss": 4.436476707458496,
+      "eval_runtime": 62.9332,
+      "eval_samples_per_second": 3.035,
+      "eval_steps_per_second": 0.381,
+      "step": 300
+    },
+    {
+      "epoch": 0.26620867325032205,
+      "grad_norm": 2.800436496734619,
+      "learning_rate": 4.037558685446009e-05,
+      "loss": 4.2769,
+      "step": 310
+    },
+    {
+      "epoch": 0.274796049806784,
+      "grad_norm": 4.590338706970215,
+      "learning_rate": 3.990610328638498e-05,
+      "loss": 4.3672,
+      "step": 320
+    },
+    {
+      "epoch": 0.28338342636324604,
+      "grad_norm": 4.552736282348633,
+      "learning_rate": 3.943661971830986e-05,
+      "loss": 4.3955,
+      "step": 330
+    },
+    {
+      "epoch": 0.291970802919708,
+      "grad_norm": 3.55195689201355,
+      "learning_rate": 3.8967136150234744e-05,
+      "loss": 4.4483,
+      "step": 340
+    },
+    {
+      "epoch": 0.30055817947617003,
+      "grad_norm": 3.1855859756469727,
+      "learning_rate": 3.8497652582159623e-05,
+      "loss": 4.2664,
+      "step": 350
+    },
+    {
+      "epoch": 0.30055817947617003,
+      "eval_loss": 4.412302017211914,
+      "eval_runtime": 62.2098,
+      "eval_samples_per_second": 3.07,
+      "eval_steps_per_second": 0.386,
+      "step": 350
+    },
+    {
+      "epoch": 0.30914555603263205,
+      "grad_norm": 4.004188537597656,
+      "learning_rate": 3.802816901408451e-05,
+      "loss": 4.1553,
+      "step": 360
+    },
+    {
+      "epoch": 0.317732932589094,
+      "grad_norm": 6.053239345550537,
+      "learning_rate": 3.755868544600939e-05,
+      "loss": 4.2626,
+      "step": 370
+    },
+    {
+      "epoch": 0.32632030914555604,
+      "grad_norm": 3.3668389320373535,
+      "learning_rate": 3.7089201877934274e-05,
+      "loss": 4.6785,
+      "step": 380
+    },
+    {
+      "epoch": 0.334907685702018,
+      "grad_norm": 3.0687854290008545,
+      "learning_rate": 3.661971830985916e-05,
+      "loss": 4.3698,
+      "step": 390
+    },
+    {
+      "epoch": 0.34349506225848003,
+      "grad_norm": 3.7815728187561035,
+      "learning_rate": 3.615023474178404e-05,
+      "loss": 4.244,
+      "step": 400
+    },
+    {
+      "epoch": 0.34349506225848003,
+      "eval_loss": 4.374711036682129,
+      "eval_runtime": 70.1476,
+      "eval_samples_per_second": 2.723,
+      "eval_steps_per_second": 0.342,
+      "step": 400
+    },
+    {
+      "epoch": 0.35208243881494206,
+      "grad_norm": 3.84957218170166,
+      "learning_rate": 3.568075117370892e-05,
+      "loss": 4.3428,
+      "step": 410
+    },
+    {
+      "epoch": 0.360669815371404,
+      "grad_norm": 3.7783055305480957,
+      "learning_rate": 3.5211267605633805e-05,
+      "loss": 4.3386,
+      "step": 420
+    },
+    {
+      "epoch": 0.36925719192786605,
+      "grad_norm": 5.324586391448975,
+      "learning_rate": 3.474178403755869e-05,
+      "loss": 4.2256,
+      "step": 430
+    },
+    {
+      "epoch": 0.377844568484328,
+      "grad_norm": 4.139454364776611,
+      "learning_rate": 3.427230046948357e-05,
+      "loss": 4.3229,
+      "step": 440
+    },
+    {
+      "epoch": 0.38643194504079004,
+      "grad_norm": 4.461709022521973,
+      "learning_rate": 3.380281690140845e-05,
+      "loss": 4.3153,
+      "step": 450
+    },
+    {
+      "epoch": 0.38643194504079004,
+      "eval_loss": 4.32847261428833,
+      "eval_runtime": 63.922,
+      "eval_samples_per_second": 2.988,
+      "eval_steps_per_second": 0.375,
+      "step": 450
+    },
+    {
+      "epoch": 0.39501932159725206,
+      "grad_norm": 3.2298669815063477,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 4.5917,
+      "step": 460
+    },
+    {
+      "epoch": 0.403606698153714,
+      "grad_norm": 2.8856964111328125,
+      "learning_rate": 3.286384976525822e-05,
+      "loss": 4.6046,
+      "step": 470
+    },
+    {
+      "epoch": 0.41219407471017605,
+      "grad_norm": 2.8745734691619873,
+      "learning_rate": 3.23943661971831e-05,
+      "loss": 4.3671,
+      "step": 480
+    },
+    {
+      "epoch": 0.420781451266638,
+      "grad_norm": 2.5535778999328613,
+      "learning_rate": 3.1924882629107986e-05,
+      "loss": 4.0099,
+      "step": 490
+    },
+    {
+      "epoch": 0.42936882782310004,
+      "grad_norm": 5.584939479827881,
+      "learning_rate": 3.1455399061032865e-05,
+      "loss": 4.3916,
+      "step": 500
+    },
+    {
+      "epoch": 0.42936882782310004,
+      "eval_loss": 4.298885822296143,
+      "eval_runtime": 63.3129,
+      "eval_samples_per_second": 3.017,
+      "eval_steps_per_second": 0.379,
+      "step": 500
+    },
+    {
+      "epoch": 0.43795620437956206,
+      "grad_norm": 5.099386692047119,
+      "learning_rate": 3.0985915492957744e-05,
+      "loss": 4.1492,
+      "step": 510
+    },
+    {
+      "epoch": 0.44654358093602403,
+      "grad_norm": 4.536731243133545,
+      "learning_rate": 3.0516431924882634e-05,
+      "loss": 4.2033,
+      "step": 520
+    },
+    {
+      "epoch": 0.45513095749248605,
+      "grad_norm": 3.5664074420928955,
+      "learning_rate": 3.0046948356807513e-05,
+      "loss": 4.008,
+      "step": 530
+    },
+    {
+      "epoch": 0.463718334048948,
+      "grad_norm": 5.168780326843262,
+      "learning_rate": 2.9577464788732395e-05,
+      "loss": 4.2175,
+      "step": 540
+    },
+    {
+      "epoch": 0.47230571060541005,
+      "grad_norm": 8.629207611083984,
+      "learning_rate": 2.9107981220657278e-05,
+      "loss": 4.2069,
+      "step": 550
+    },
+    {
+      "epoch": 0.47230571060541005,
+      "eval_loss": 4.260441780090332,
+      "eval_runtime": 64.1132,
+      "eval_samples_per_second": 2.979,
+      "eval_steps_per_second": 0.374,
+      "step": 550
+    },
+    {
+      "epoch": 0.48089308716187207,
+      "grad_norm": 4.587916374206543,
+      "learning_rate": 2.8638497652582164e-05,
+      "loss": 4.3667,
+      "step": 560
+    },
+    {
+      "epoch": 0.48948046371833404,
+      "grad_norm": 3.883270502090454,
+      "learning_rate": 2.8169014084507046e-05,
+      "loss": 4.2119,
+      "step": 570
+    },
+    {
+      "epoch": 0.49806784027479606,
+      "grad_norm": 5.901604175567627,
+      "learning_rate": 2.7699530516431926e-05,
+      "loss": 4.1281,
+      "step": 580
+    },
+    {
+      "epoch": 0.506655216831258,
+      "grad_norm": 4.998931407928467,
+      "learning_rate": 2.7230046948356808e-05,
+      "loss": 4.1441,
+      "step": 590
+    },
+    {
+      "epoch": 0.51524259338772,
+      "grad_norm": 3.0025761127471924,
+      "learning_rate": 2.676056338028169e-05,
+      "loss": 4.8223,
+      "step": 600
+    },
+    {
+      "epoch": 0.51524259338772,
+      "eval_loss": 4.239251613616943,
+      "eval_runtime": 65.3752,
+      "eval_samples_per_second": 2.922,
+      "eval_steps_per_second": 0.367,
+      "step": 600
+    },
+    {
+      "epoch": 0.5238299699441821,
+      "grad_norm": 4.234139442443848,
+      "learning_rate": 2.6291079812206577e-05,
+      "loss": 4.3137,
+      "step": 610
+    },
+    {
+      "epoch": 0.5324173465006441,
+      "grad_norm": 6.55452823638916,
+      "learning_rate": 2.5821596244131456e-05,
+      "loss": 4.1674,
+      "step": 620
+    },
+    {
+      "epoch": 0.541004723057106,
+      "grad_norm": 4.998346328735352,
+      "learning_rate": 2.535211267605634e-05,
+      "loss": 4.09,
+      "step": 630
+    },
+    {
+      "epoch": 0.549592099613568,
+      "grad_norm": 5.1507182121276855,
+      "learning_rate": 2.4882629107981224e-05,
+      "loss": 4.1919,
+      "step": 640
+    },
+    {
+      "epoch": 0.55817947617003,
+      "grad_norm": 3.014167308807373,
+      "learning_rate": 2.4413145539906104e-05,
+      "loss": 4.2866,
+      "step": 650
+    },
+    {
+      "epoch": 0.55817947617003,
+      "eval_loss": 4.213797569274902,
+      "eval_runtime": 64.5488,
+      "eval_samples_per_second": 2.959,
+      "eval_steps_per_second": 0.372,
+      "step": 650
+    },
+    {
+      "epoch": 0.5667668527264921,
+      "grad_norm": 3.4198052883148193,
+      "learning_rate": 2.3943661971830986e-05,
+      "loss": 4.2091,
+      "step": 660
+    },
+    {
+      "epoch": 0.5753542292829541,
+      "grad_norm": 3.070835590362549,
+      "learning_rate": 2.347417840375587e-05,
+      "loss": 4.2072,
+      "step": 670
+    },
+    {
+      "epoch": 0.583941605839416,
+      "grad_norm": 4.2921833992004395,
+      "learning_rate": 2.300469483568075e-05,
+      "loss": 4.235,
+      "step": 680
+    },
+    {
+      "epoch": 0.592528982395878,
+      "grad_norm": 3.4526073932647705,
+      "learning_rate": 2.2535211267605634e-05,
+      "loss": 4.0161,
+      "step": 690
+    },
+    {
+      "epoch": 0.6011163589523401,
+      "grad_norm": 3.8680613040924072,
+      "learning_rate": 2.2065727699530516e-05,
+      "loss": 3.9724,
+      "step": 700
+    },
+    {
+      "epoch": 0.6011163589523401,
+      "eval_loss": 4.210733413696289,
+      "eval_runtime": 65.7734,
+      "eval_samples_per_second": 2.904,
+      "eval_steps_per_second": 0.365,
+      "step": 700
+    },
+    {
+      "epoch": 0.6097037355088021,
+      "grad_norm": 3.843921422958374,
+      "learning_rate": 2.1596244131455402e-05,
+      "loss": 4.1656,
+      "step": 710
+    },
+    {
+      "epoch": 0.6182911120652641,
+      "grad_norm": 2.2914586067199707,
+      "learning_rate": 2.112676056338028e-05,
+      "loss": 4.2278,
+      "step": 720
+    },
+    {
+      "epoch": 0.626878488621726,
+      "grad_norm": 4.322068691253662,
+      "learning_rate": 2.0657276995305167e-05,
+      "loss": 4.2945,
+      "step": 730
+    },
+    {
+      "epoch": 0.635465865178188,
+      "grad_norm": 3.5365047454833984,
+      "learning_rate": 2.0187793427230047e-05,
+      "loss": 4.4492,
+      "step": 740
+    },
+    {
+      "epoch": 0.6440532417346501,
+      "grad_norm": 2.4377028942108154,
+      "learning_rate": 1.971830985915493e-05,
+      "loss": 4.3448,
+      "step": 750
+    },
+    {
+      "epoch": 0.6440532417346501,
+      "eval_loss": 4.160037517547607,
+      "eval_runtime": 63.1058,
+      "eval_samples_per_second": 3.027,
+      "eval_steps_per_second": 0.38,
+      "step": 750
+    },
+    {
+      "epoch": 0.6526406182911121,
+      "grad_norm": 2.93143367767334,
+      "learning_rate": 1.9248826291079812e-05,
+      "loss": 4.2937,
+      "step": 760
+    },
+    {
+      "epoch": 0.6612279948475741,
+      "grad_norm": 3.1724581718444824,
+      "learning_rate": 1.8779342723004694e-05,
+      "loss": 4.1608,
+      "step": 770
+    },
+    {
+      "epoch": 0.669815371404036,
+      "grad_norm": 5.938080310821533,
+      "learning_rate": 1.830985915492958e-05,
+      "loss": 4.204,
+      "step": 780
+    },
+    {
+      "epoch": 0.678402747960498,
+      "grad_norm": 4.775387287139893,
+      "learning_rate": 1.784037558685446e-05,
+      "loss": 4.2206,
+      "step": 790
+    },
+    {
+      "epoch": 0.6869901245169601,
+      "grad_norm": 3.222551107406616,
+      "learning_rate": 1.7370892018779345e-05,
+      "loss": 4.2675,
+      "step": 800
+    },
+    {
+      "epoch": 0.6869901245169601,
+      "eval_loss": 4.140951156616211,
+      "eval_runtime": 64.3615,
+      "eval_samples_per_second": 2.968,
+      "eval_steps_per_second": 0.373,
+      "step": 800
+    },
+    {
+      "epoch": 0.6955775010734221,
+      "grad_norm": 4.13527774810791,
+      "learning_rate": 1.6901408450704224e-05,
+      "loss": 4.038,
+      "step": 810
+    },
+    {
+      "epoch": 0.7041648776298841,
+      "grad_norm": 3.364672899246216,
+      "learning_rate": 1.643192488262911e-05,
+      "loss": 4.0547,
+      "step": 820
+    },
+    {
+      "epoch": 0.712752254186346,
+      "grad_norm": 4.023569583892822,
+      "learning_rate": 1.5962441314553993e-05,
+      "loss": 4.1736,
+      "step": 830
+    },
+    {
+      "epoch": 0.721339630742808,
+      "grad_norm": 3.6011292934417725,
+      "learning_rate": 1.5492957746478872e-05,
+      "loss": 4.0854,
+      "step": 840
+    },
+    {
+      "epoch": 0.7299270072992701,
+      "grad_norm": 3.8368685245513916,
+      "learning_rate": 1.5023474178403756e-05,
+      "loss": 4.1082,
+      "step": 850
+    },
+    {
+      "epoch": 0.7299270072992701,
+      "eval_loss": 4.111354351043701,
+      "eval_runtime": 60.749,
+      "eval_samples_per_second": 3.144,
+      "eval_steps_per_second": 0.395,
+      "step": 850
+    },
+    {
+      "epoch": 0.7385143838557321,
+      "grad_norm": 7.593260288238525,
+      "learning_rate": 1.4553990610328639e-05,
+      "loss": 3.9598,
+      "step": 860
+    },
+    {
+      "epoch": 0.7471017604121941,
+      "grad_norm": 2.3877692222595215,
+      "learning_rate": 1.4084507042253523e-05,
+      "loss": 4.0798,
+      "step": 870
+    },
+    {
+      "epoch": 0.755689136968656,
+      "grad_norm": 3.5253055095672607,
+      "learning_rate": 1.3615023474178404e-05,
+      "loss": 4.0939,
+      "step": 880
+    },
+    {
+      "epoch": 0.764276513525118,
+      "grad_norm": 3.1843645572662354,
+      "learning_rate": 1.3145539906103288e-05,
+      "loss": 4.3067,
+      "step": 890
+    },
+    {
+      "epoch": 0.7728638900815801,
+      "grad_norm": 3.8724074363708496,
+      "learning_rate": 1.267605633802817e-05,
+      "loss": 3.7572,
+      "step": 900
+    },
+    {
+      "epoch": 0.7728638900815801,
+      "eval_loss": 4.097023010253906,
+      "eval_runtime": 65.5665,
+      "eval_samples_per_second": 2.913,
+      "eval_steps_per_second": 0.366,
+      "step": 900
+    },
+    {
+      "epoch": 0.7814512666380421,
+      "grad_norm": 2.892914295196533,
+      "learning_rate": 1.2206572769953052e-05,
+      "loss": 3.8861,
+      "step": 910
+    },
+    {
+      "epoch": 0.7900386431945041,
+      "grad_norm": 3.4761860370635986,
+      "learning_rate": 1.1737089201877934e-05,
+      "loss": 3.9094,
+      "step": 920
+    },
+    {
+      "epoch": 0.798626019750966,
+      "grad_norm": 3.8408806324005127,
+      "learning_rate": 1.1267605633802817e-05,
+      "loss": 3.7834,
+      "step": 930
+    },
+    {
+      "epoch": 0.807213396307428,
+      "grad_norm": 4.407979488372803,
+      "learning_rate": 1.0798122065727701e-05,
+      "loss": 3.9476,
+      "step": 940
+    },
+    {
+      "epoch": 0.8158007728638901,
+      "grad_norm": 3.1799418926239014,
+      "learning_rate": 1.0328638497652584e-05,
+      "loss": 3.8357,
+      "step": 950
+    },
+    {
+      "epoch": 0.8158007728638901,
+      "eval_loss": 4.082327365875244,
+      "eval_runtime": 67.6425,
+      "eval_samples_per_second": 2.824,
+      "eval_steps_per_second": 0.355,
+      "step": 950
+    },
+    {
+      "epoch": 0.8243881494203521,
+      "grad_norm": 1.7509279251098633,
+      "learning_rate": 9.859154929577465e-06,
+      "loss": 4.4142,
+      "step": 960
+    },
+    {
+      "epoch": 0.8329755259768141,
+      "grad_norm": 4.1650590896606445,
+      "learning_rate": 9.389671361502347e-06,
+      "loss": 3.9477,
+      "step": 970
+    },
+    {
+      "epoch": 0.841562902533276,
+      "grad_norm": 3.6541409492492676,
+      "learning_rate": 8.92018779342723e-06,
+      "loss": 4.1559,
+      "step": 980
+    },
+    {
+      "epoch": 0.8501502790897381,
+      "grad_norm": 4.61195182800293,
+      "learning_rate": 8.450704225352112e-06,
+      "loss": 3.9817,
+      "step": 990
+    },
+    {
+      "epoch": 0.8587376556462001,
+      "grad_norm": 5.288261413574219,
+      "learning_rate": 7.981220657276996e-06,
+      "loss": 3.9061,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8587376556462001,
+      "eval_loss": 4.065762042999268,
+      "eval_runtime": 68.5381,
+      "eval_samples_per_second": 2.787,
+      "eval_steps_per_second": 0.35,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8673250322026621,
+      "grad_norm": 3.5798919200897217,
+      "learning_rate": 7.511737089201878e-06,
+      "loss": 3.6328,
+      "step": 1010
+    },
+    {
+      "epoch": 0.8759124087591241,
+      "grad_norm": 4.841778755187988,
+      "learning_rate": 7.042253521126762e-06,
+      "loss": 4.1492,
+      "step": 1020
+    },
+    {
+      "epoch": 0.884499785315586,
+      "grad_norm": 3.2941842079162598,
+      "learning_rate": 6.572769953051644e-06,
+      "loss": 4.1032,
+      "step": 1030
+    },
+    {
+      "epoch": 0.8930871618720481,
+      "grad_norm": 3.6030590534210205,
+      "learning_rate": 6.103286384976526e-06,
+      "loss": 4.0264,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9016745384285101,
+      "grad_norm": 4.33119010925293,
+      "learning_rate": 5.6338028169014084e-06,
+      "loss": 3.8422,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9016745384285101,
+      "eval_loss": 4.055400848388672,
+      "eval_runtime": 57.5759,
+      "eval_samples_per_second": 3.317,
+      "eval_steps_per_second": 0.417,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9102619149849721,
+      "grad_norm": 3.8521981239318848,
+      "learning_rate": 5.164319248826292e-06,
+      "loss": 3.6974,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9188492915414341,
+      "grad_norm": 3.1546719074249268,
+      "learning_rate": 4.6948356807511736e-06,
+      "loss": 3.9701,
+      "step": 1070
+    },
+    {
+      "epoch": 0.927436668097896,
+      "grad_norm": 14.868404388427734,
+      "learning_rate": 4.225352112676056e-06,
+      "loss": 3.9999,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9360240446543581,
+      "grad_norm": 4.882206439971924,
+      "learning_rate": 3.755868544600939e-06,
+      "loss": 3.976,
+      "step": 1090
+    },
+    {
+      "epoch": 0.9446114212108201,
+      "grad_norm": 2.768838405609131,
+      "learning_rate": 3.286384976525822e-06,
+      "loss": 4.0052,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9446114212108201,
+      "eval_loss": 4.045039653778076,
+      "eval_runtime": 64.0192,
+      "eval_samples_per_second": 2.983,
+      "eval_steps_per_second": 0.375,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9531987977672821,
+      "grad_norm": 3.4784746170043945,
+      "learning_rate": 2.8169014084507042e-06,
+      "loss": 4.0742,
+      "step": 1110
+    },
+    {
+      "epoch": 0.9617861743237441,
+      "grad_norm": 10.850025177001953,
+      "learning_rate": 2.3474178403755868e-06,
+      "loss": 4.0734,
+      "step": 1120
+    },
+    {
+      "epoch": 0.970373550880206,
+      "grad_norm": 3.2946884632110596,
+      "learning_rate": 1.8779342723004696e-06,
+      "loss": 3.8664,
+      "step": 1130
+    },
+    {
+      "epoch": 0.9789609274366681,
+      "grad_norm": 2.7389168739318848,
+      "learning_rate": 1.4084507042253521e-06,
+      "loss": 4.0202,
+      "step": 1140
+    },
+    {
+      "epoch": 0.9875483039931301,
+      "grad_norm": 4.516402244567871,
+      "learning_rate": 9.389671361502348e-07,
+      "loss": 3.9611,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9875483039931301,
+      "eval_loss": 4.035213947296143,
+      "eval_runtime": 65.9442,
+      "eval_samples_per_second": 2.896,
+      "eval_steps_per_second": 0.364,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9961356805495921,
+      "grad_norm": 7.425461769104004,
+      "learning_rate": 4.694835680751174e-07,
+      "loss": 4.0171,
+      "step": 1160
+    },
+    {
+      "epoch": 1.0,
+      "step": 1165,
+      "total_flos": 0.0,
+      "train_loss": 4.406593790995717,
+      "train_runtime": 4471.1894,
+      "train_samples_per_second": 2.084,
+      "train_steps_per_second": 0.261
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1165,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

kn/chatterbox-kannada-tts/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:820ae2283c22956087467c090423666c0a0c0f43c70fc3b6f4a15c83bee791f4
+size 5496

kn/chatterbox-kannada-tts/ve.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0921cab452fa278bc25cd23ffd59d36f816d7dc5181dd1bef9751a7fb61f63c
+size 5695784