Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,5 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.mlpackage filter=lfs diff=lfs merge=lfs -text
+*.mlpackage/** filter=lfs diff=lfs merge=lfs -text
+weights/** 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
+*.nemo filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+---
+license: cc-by-4.0
+language:
+  - en
+tags:
+  - asr
+  - speech
+  - coreml
+  - nemo
+  - parakeet
+  - nvidia
+  - 6bit-palettize-kmeans
+library_name: coremltools
+pipeline_tag: automatic-speech-recognition
+base_model: nvidia/parakeet-tdt-0.6b-v2
+---
+
+# parakeet-tdt-0.6b-v2-coreml-6bit
+
+CoreML conversion of [nvidia/parakeet-tdt-0.6b-v2](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2) — 6BIT PALETTIZE KMEANS quantized.
+
+| | |
+|---|---|
+| **Architecture** | TDT (Token-and-Duration Transducer) |
+| **Language** | English |
+| **Sample rate** | 16000 Hz |
+| **Max audio** | 15.0s |
+| **Vocab size** | 1024 |
+| **Framework** | NVIDIA NeMo → CoreML (coremltools) |
+
+## Components
+
+| File | Component | Best compute |
+|------|-----------|--------------|
+| `parakeet_mel_encoder.mlpackage` | mel_encoder | ANE / GPU |
+| `parakeet_decoder.mlpackage` | decoder | CPU only |
+| `parakeet_joint_decision_single_step.mlpackage` | joint_decision_single_step | ANE / GPU |
+
+## Usage
+
+```bash
+pip install ovos-stt-plugin-coreml
+```
+
+```python
+from ovos_stt_plugin_coreml import CoremlSTT
+from ovos_plugin_manager.utils.audio import AudioFile
+
+stt = CoremlSTT(config={"metadata": "metadata.json"})
+
+with AudioFile("speech.wav") as f:
+    audio = f.read()
+print(stt.execute(audio))
+```
+
+## Source model
+
+[nvidia/parakeet-tdt-0.6b-v2](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2)
+

infer.py

@@ -0,0 +1,79 @@
+#!/usr/bin/env python3
+"""Greedy TDT/RNNT inference with CoreML parakeet-tdt-0.6b-v2.
+
+Usage:  python infer.py audio.wav
+"""
+import json, sys
+from pathlib import Path
+
+import coremltools as ct
+import numpy as np
+import soundfile as sf
+
+REPO_DIR = Path(__file__).parent
+SAMPLE_RATE = 16_000
+
+def load_audio(path, max_samples):
+    data, sr = sf.read(path, dtype="float32", always_2d=False)
+    if sr != SAMPLE_RATE: raise ValueError(f"Expected {SAMPLE_RATE} Hz.")
+    if data.ndim > 1: data = data[:, 0]
+    actual = min(len(data), max_samples)
+    data = np.pad(data, (0, max(0, max_samples - len(data))))[:max_samples]
+    return data.reshape(1, -1).astype(np.float32), actual
+
+def transcribe(audio_path, compute_units="ALL"):
+    meta  = json.loads((REPO_DIR / "metadata.json").read_text())
+    vocab = json.loads((REPO_DIR / "vocab.json").read_text())
+    blank = meta["blank_id"]
+    n     = meta["max_audio_samples"]
+    bins  = meta.get("duration_bins", [1])
+    comps = meta["components"]["decoder"]["inputs"]
+    d_layers = comps["h_in"][0]
+    d_hidden = comps["h_in"][2]
+
+    cu_map = {"ALL": ct.ComputeUnit.ALL, "CPU_ONLY": ct.ComputeUnit.CPU_ONLY,
+               "CPU_AND_NE": ct.ComputeUnit.CPU_AND_NE}
+    cu = cu_map.get(compute_units.upper(), ct.ComputeUnit.ALL)
+    mel_enc  = ct.models.MLModel(str(REPO_DIR / "parakeet_mel_encoder.mlpackage"), compute_units=cu)
+    dec_model = ct.models.MLModel(str(REPO_DIR / "parakeet_decoder.mlpackage"),
+                                  compute_units=ct.ComputeUnit.CPU_ONLY)
+    jd_model  = ct.models.MLModel(str(REPO_DIR / "parakeet_joint_decision_single_step.mlpackage"),
+                                  compute_units=cu)
+
+    audio, actual = load_audio(audio_path, n)
+    length = np.array([actual], dtype=np.int32)
+    enc_out  = mel_enc.predict({"audio_signal": audio, "audio_length": length})
+    encoder  = enc_out["encoder"]
+    enc_len  = int(enc_out["encoder_length"][0])
+
+    h = np.zeros((d_layers, 1, d_hidden), dtype=np.float32)
+    c = np.zeros((d_layers, 1, d_hidden), dtype=np.float32)
+    prev  = np.array([[blank]], dtype=np.int32)
+    tlen  = np.array([1], dtype=np.int32)
+    dec_out = dec_model.predict({"targets": prev, "target_length": tlen, "h_in": h, "c_in": c})
+    dec_state, h, c = dec_out["decoder"], dec_out["h_out"], dec_out["c_out"]
+
+    tokens, t = [], 0
+    while t < enc_len:
+        jd  = jd_model.predict({"encoder_step": encoder[:,:,t:t+1], "decoder_step": dec_state[:,:,:1]})
+        tok = int(jd["token_id"].flat[0])
+        dur = int(jd["duration"].flat[0])
+        adv = bins[min(dur, len(bins)-1)] if bins else 1
+        if tok != blank:
+            tokens.append(tok)
+            dec_out = dec_model.predict({"targets": np.array([[tok]], dtype=np.int32),
+                                          "target_length": tlen, "h_in": h, "c_in": c})
+            dec_state, h, c = dec_out["decoder"], dec_out["h_out"], dec_out["c_out"]
+        t += max(1, adv)
+
+    return "".join(vocab[i] for i in tokens if i < len(vocab)).replace("▁", " ").strip()
+
+if __name__ == "__main__":
+    args = sys.argv[1:]
+    if not args:
+        print("Usage: python infer.py <audio.wav> [--compute-units ALL|CPU_ONLY|CPU_AND_NE]")
+        sys.exit(1)
+    cu = "ALL"
+    if "--compute-units" in args:
+        cu = args[args.index("--compute-units") + 1]
+    print(transcribe(args[0], cu))

metadata.json

@@ -0,0 +1,121 @@
+{
+  "model_id": "nvidia/parakeet-tdt-0.6b-v2",
+  "model_type": "parakeet_tdt_rnnt",
+  "language": "",
+  "sample_rate": 16000,
+  "max_audio_seconds": 15.0,
+  "max_audio_samples": 240000,
+  "vocab_size": 1024,
+  "blank_id": 1024,
+  "checkpoint": {
+    "type": "pretrained",
+    "model_id": "nvidia/parakeet-tdt-0.6b-v2"
+  },
+  "coreml": {
+    "compute_precision": "FLOAT32",
+    "quantization": "6bit_palettize_kmeans"
+  },
+  "components": {
+    "mel_encoder": {
+      "path": "parakeet_mel_encoder.mlpackage",
+      "inputs": {
+        "audio_signal": [
+          1,
+          240000
+        ],
+        "audio_length": [
+          1
+        ]
+      },
+      "outputs": {
+        "encoder": [
+          1,
+          1024,
+          188
+        ],
+        "encoder_length": [
+          1
+        ]
+      }
+    },
+    "decoder": {
+      "path": "parakeet_decoder.mlpackage",
+      "inputs": {
+        "targets": [
+          1,
+          1
+        ],
+        "target_length": [
+          1
+        ],
+        "h_in": [
+          2,
+          1,
+          640
+        ],
+        "c_in": [
+          2,
+          1,
+          640
+        ]
+      },
+      "outputs": {
+        "decoder": [
+          1,
+          640,
+          1
+        ],
+        "h_out": [
+          2,
+          1,
+          640
+        ],
+        "c_out": [
+          2,
+          1,
+          640
+        ]
+      }
+    },
+    "joint_decision_single_step": {
+      "path": "parakeet_joint_decision_single_step.mlpackage",
+      "inputs": {
+        "encoder_step": [
+          1,
+          1024,
+          1
+        ],
+        "decoder_step": [
+          1,
+          640,
+          1
+        ]
+      },
+      "outputs": {
+        "token_id": [
+          1,
+          1,
+          1
+        ],
+        "token_prob": [
+          1,
+          1,
+          1
+        ],
+        "duration": [
+          1,
+          1,
+          1
+        ]
+      }
+    }
+  },
+  "joint_extra_outputs": 5,
+  "duration_bins": [
+    0,
+    1,
+    2,
+    3,
+    4
+  ]
+}

parakeet_decoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a0f433cb19fbfd5fe93c4c914ee86cf3b8d979285432dc97fe60705b4dd81d0
+size 13056

parakeet_decoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4237b9ebc96622cdf603a394c2ed77937b33ecef22d091ab85fe63439a246928
+size 5418944

parakeet_decoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "4010B768-B6C9-4BAF-B8C3-B3E2B846F1DC": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "476E9C69-4E70-4E21-B692-76D907E1BAF8": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "4010B768-B6C9-4BAF-B8C3-B3E2B846F1DC"
+}

parakeet_joint_decision_single_step.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eda306529b9596000ed41fbac08cb7aaaffe3f886954def45eb4a8acd53b3fd
+size 8903

parakeet_joint_decision_single_step.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee7256372489e0031a32a46ed0e34d6c4953d1b7990893917ee29f7900c1517
+size 1298764

parakeet_joint_decision_single_step.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "01C05737-BEB1-4E6E-B101-091E617528EC": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "9F5BC695-2F83-4328-BB7C-AC0667F7875C": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "01C05737-BEB1-4E6E-B101-091E617528EC"
+}

parakeet_mel_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b3a5a5531c9a75753fd2848a93f8a69ed94e7c09a5b6ebe7c67e4e1de61108b
+size 694779

parakeet_mel_encoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b4c9f194bad0f80473216269bcc362a59e6dde2d4bf567d48c9ee36a49104d1
+size 445554432

parakeet_mel_encoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "2DE0C841-4ED6-4BDB-909C-C03FD4989E39": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "6558255C-67C4-4F38-91C3-C2232C27FCA8": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "2DE0C841-4ED6-4BDB-909C-C03FD4989E39"
+}

quantization_summary.json

@@ -0,0 +1,17 @@
+{
+  "parakeet_decoder": {
+    "original_mb": 13.8,
+    "6bit_mb": 5.2,
+    "compression": 2.66
+  },
+  "parakeet_joint_decision_single_step": {
+    "original_mb": 3.3,
+    "6bit_mb": 1.2,
+    "compression": 2.65
+  },
+  "parakeet_mel_encoder": {
+    "original_mb": 1132.5,
+    "6bit_mb": 425.6,
+    "compression": 2.66
+  }
+}

vocab.json

@@ -0,0 +1,1026 @@
+[
+  "<unk>",
+  "▁t",
+  "▁th",
+  "▁a",
+  "in",
+  "▁the",
+  "re",
+  "▁w",
+  "▁o",
+  "▁s",
+  "at",
+  "ou",
+  "er",
+  "nd",
+  "▁i",
+  "▁b",
+  "▁c",
+  "on",
+  "▁h",
+  "ing",
+  "▁to",
+  "▁m",
+  "en",
+  "▁f",
+  "▁p",
+  "an",
+  "▁d",
+  "es",
+  "or",
+  "ll",
+  "▁of",
+  "▁and",
+  "▁y",
+  "▁l",
+  "▁I",
+  "it",
+  "▁in",
+  "is",
+  "ed",
+  "▁g",
+  "▁you",
+  "ar",
+  "▁that",
+  "om",
+  "as",
+  "▁n",
+  "ve",
+  "us",
+  "ic",
+  "ow",
+  "al",
+  "▁it",
+  "▁be",
+  "▁wh",
+  "le",
+  "ion",
+  "ut",
+  "ot",
+  "▁we",
+  "▁is",
+  "▁e",
+  "et",
+  "ay",
+  "▁re",
+  "▁on",
+  "▁T",
+  "▁A",
+  "▁ha",
+  "ent",
+  "ke",
+  "ct",
+  "▁S",
+  "ig",
+  "ver",
+  "▁Th",
+  "all",
+  "id",
+  "▁for",
+  "ro",
+  "▁he",
+  "se",
+  "▁this",
+  "ld",
+  "ly",
+  "▁go",
+  "▁k",
+  "▁st",
+  "st",
+  "ch",
+  "▁li",
+  "▁u",
+  "am",
+  "ur",
+  "ce",
+  "ith",
+  "im",
+  "▁so",
+  "▁have",
+  "▁do",
+  "ht",
+  "th",
+  "▁an",
+  "▁with",
+  "ad",
+  "▁r",
+  "ir",
+  "▁was",
+  "▁as",
+  "▁W",
+  "▁are",
+  "ust",
+  "ally",
+  "▁j",
+  "▁se",
+  "ation",
+  "od",
+  "ere",
+  "▁like",
+  "▁not",
+  "▁kn",
+  "ight",
+  "▁B",
+  "▁they",
+  "▁And",
+  "▁know",
+  "ome",
+  "op",
+  "▁can",
+  "▁or",
+  "▁sh",
+  "▁me",
+  "ill",
+  "ant",
+  "ck",
+  "▁what",
+  "▁at",
+  "▁ab",
+  "ould",
+  "ol",
+  "▁So",
+  "▁C",
+  "use",
+  "ter",
+  "il",
+  "▁but",
+  "▁just",
+  "▁ne",
+  "▁de",
+  "ra",
+  "ore",
+  "▁there",
+  "ul",
+  "out",
+  "▁con",
+  "▁all",
+  "▁The",
+  "ers",
+  "▁H",
+  "▁fr",
+  "▁pro",
+  "ge",
+  "ea",
+  "▁Y",
+  "▁O",
+  "▁M",
+  "pp",
+  "▁com",
+  "ess",
+  "▁ch",
+  "▁al",
+  "est",
+  "ate",
+  "qu",
+  "▁lo",
+  "▁ex",
+  "very",
+  "▁su",
+  "ain",
+  "▁one",
+  "ca",
+  "art",
+  "ist",
+  "if",
+  "ive",
+  "▁if",
+  "ink",
+  "nt",
+  "ab",
+  "▁about",
+  "▁going",
+  "▁v",
+  "▁wor",
+  "um",
+  "ok",
+  "▁your",
+  "▁my",
+  "ind",
+  "▁get",
+  "cause",
+  "▁from",
+  "▁don",
+  "ri",
+  "pe",
+  "un",
+  "ity",
+  "▁up",
+  "▁P",
+  "▁out",
+  "ort",
+  "▁L",
+  "ment",
+  "el",
+  "▁N",
+  "▁some",
+  "ich",
+  "and",
+  "▁think",
+  "em",
+  "oug",
+  "▁G",
+  "os",
+  "▁D",
+  "res",
+  "▁because",
+  "▁by",
+  "ake",
+  "▁int",
+  "ie",
+  "▁us",
+  "▁tr",
+  "▁then",
+  "ack",
+  "▁pl",
+  "▁here",
+  "▁pe",
+  "her",
+  "▁will",
+  "▁F",
+  "▁which",
+  "ard",
+  "▁right",
+  "▁thing",
+  "▁want",
+  "ies",
+  "ople",
+  "▁It",
+  "▁them",
+  "ame",
+  "▁We",
+  "our",
+  "▁say",
+  "▁R",
+  "▁people",
+  "▁see",
+  "▁who",
+  "ast",
+  "ure",
+  "ect",
+  "ear",
+  "▁tim",
+  "▁E",
+  "▁You",
+  "▁would",
+  "▁when",
+  "ven",
+  "▁our",
+  "ci",
+  "▁really",
+  "▁more",
+  "ound",
+  "ose",
+  "ak",
+  "▁co",
+  "ide",
+  "ough",
+  "▁had",
+  "so",
+  "▁qu",
+  "eah",
+  "▁were",
+  "ine",
+  "▁act",
+  "ther",
+  "▁these",
+  "▁how",
+  "▁now",
+  "▁sa",
+  "ud",
+  "▁Wh",
+  "▁man",
+  "ous",
+  "one",
+  "pt",
+  "ff",
+  "ong",
+  "▁has",
+  "▁any",
+  "▁very",
+  "▁But",
+  "▁look",
+  "iv",
+  "itt",
+  "▁time",
+  "▁mo",
+  "▁ar",
+  "hing",
+  "▁le",
+  "▁work",
+  "▁their",
+  "are",
+  "▁his",
+  "per",
+  "ions",
+  "▁im",
+  "▁ag",
+  "▁J",
+  "▁no",
+  "▁en",
+  "▁got",
+  "ag",
+  "▁sp",
+  "ans",
+  "act",
+  "▁te",
+  "▁also",
+  "iz",
+  "ice",
+  "▁That",
+  "▁cl",
+  "▁been",
+  "▁way",
+  "▁fe",
+  "▁did",
+  "ple",
+  "ually",
+  "▁other",
+  "▁U",
+  "ite",
+  "age",
+  "omet",
+  "ber",
+  "reat",
+  "ree",
+  "▁into",
+  "own",
+  "▁tw",
+  "▁part",
+  "alk",
+  "▁where",
+  "▁need",
+  "▁every",
+  "pl",
+  "▁ad",
+  "ry",
+  "▁over",
+  "ble",
+  "ap",
+  "ue",
+  "▁kind",
+  "▁po",
+  "▁back",
+  "▁cont",
+  "iff",
+  "▁somet",
+  "▁pr",
+  "nder",
+  "ire",
+  "▁good",
+  "▁than",
+  "ace",
+  "▁gu",
+  "ep",
+  "og",
+  "ick",
+  "way",
+  "▁lot",
+  "▁un",
+  "▁things",
+  "▁In",
+  "ish",
+  "kay",
+  "▁well",
+  "▁could",
+  "▁pre",
+  "▁two",
+  "irst",
+  "▁diff",
+  "ach",
+  "cc",
+  "ittle",
+  "int",
+  "▁He",
+  "▁those",
+  "ence",
+  "ip",
+  "ase",
+  "▁him",
+  "▁make",
+  "▁little",
+  "ical",
+  "▁gr",
+  "▁year",
+  "ass",
+  "▁thr",
+  "uch",
+  "ated",
+  "▁This",
+  "▁off",
+  "▁res",
+  "ac",
+  "ance",
+  "▁actually",
+  "▁talk",
+  "ult",
+  "able",
+  "orm",
+  "▁dis",
+  "▁first",
+  "ations",
+  "▁something",
+  "▁she",
+  "sel",
+  "▁let",
+  "ord",
+  "▁may",
+  "ia",
+  "▁am",
+  "▁her",
+  "▁said",
+  "▁bo",
+  "be",
+  "ount",
+  "▁much",
+  "▁per",
+  "▁even",
+  "▁differe",
+  "vel",
+  "ary",
+  "▁app",
+  "ving",
+  "▁comm",
+  "▁imp",
+  "ys",
+  "▁again",
+  "ress",
+  "▁yeah",
+  "▁down",
+  "ang",
+  "▁mean",
+  "na",
+  "ens",
+  "▁does",
+  "▁fo",
+  "▁comp",
+  "▁ro",
+  "▁bl",
+  "ody",
+  "▁K",
+  "▁through",
+  "▁start",
+  "uct",
+  "▁only",
+  "▁bet",
+  "▁under",
+  "▁br",
+  "▁take",
+  "ning",
+  "▁bu",
+  "▁use",
+  "▁Ch",
+  "xt",
+  "co",
+  "ory",
+  "ild",
+  "▁put",
+  "▁call",
+  "▁new",
+  "other",
+  "ting",
+  "▁happ",
+  "ater",
+  "▁inc",
+  "ition",
+  "▁different",
+  "▁should",
+  "ade",
+  "ign",
+  "thing",
+  "▁day",
+  "fore",
+  "▁Yeah",
+  "ark",
+  "ile",
+  "ial",
+  "▁come",
+  "▁They",
+  "▁being",
+  "▁try",
+  "ious",
+  "▁sc",
+  "▁bit",
+  "▁spe",
+  "ub",
+  "fe",
+  "▁doing",
+  "▁St",
+  "vers",
+  "av",
+  "ty",
+  "ian",
+  "onna",
+  "red",
+  "wn",
+  "▁ke",
+  "form",
+  "ors",
+  "▁fl",
+  "fter",
+  "ail",
+  "ents",
+  "▁gonna",
+  "▁point",
+  "ces",
+  "▁There",
+  "self",
+  "▁many",
+  "▁If",
+  "▁same",
+  "▁sy",
+  "▁quest",
+  "▁most",
+  "▁great",
+  "▁What",
+  "▁fu",
+  "ug",
+  "▁show",
+  "we",
+  "ual",
+  "ons",
+  "▁Be",
+  "ically",
+  "▁ser",
+  "▁rem",
+  "▁ind",
+  "▁pers",
+  "▁V",
+  "he",
+  "▁str",
+  "ved",
+  "▁still",
+  "ank",
+  "▁rec",
+  "▁wr",
+  "ought",
+  "day",
+  "ath",
+  "▁end",
+  "▁bas",
+  "ft",
+  "erm",
+  "body",
+  "ph",
+  "ject",
+  "ict",
+  "▁play",
+  "▁Is",
+  "ates",
+  "▁ph",
+  "oth",
+  "▁acc",
+  "get",
+  "▁years",
+  "▁em",
+  "▁id",
+  "▁Oh",
+  "ves",
+  "ever",
+  "▁inter",
+  "▁rel",
+  "▁before",
+  "▁feel",
+  "igh",
+  "▁three",
+  "iss",
+  "▁des",
+  "ne",
+  "▁why",
+  "▁uh",
+  "▁To",
+  "▁cons",
+  "▁hel",
+  "▁after",
+  "ower",
+  "urn",
+  "▁okay",
+  "▁long",
+  "▁bel",
+  "▁around",
+  "ful",
+  "te",
+  "ise",
+  "▁ob",
+  "▁supp",
+  "ady",
+  "ange",
+  "aking",
+  "▁pos",
+  "atch",
+  "▁tra",
+  "gr",
+  "▁might",
+  "ert",
+  "▁help",
+  "ost",
+  "▁too",
+  "cial",
+  "▁world",
+  "▁give",
+  "ike",
+  "▁Okay",
+  "ways",
+  "▁min",
+  "ward",
+  "ily",
+  "▁gen",
+  "▁find",
+  "▁dec",
+  "ular",
+  "ob",
+  "▁tell",
+  "▁Now",
+  "▁sm",
+  "▁cour",
+  "▁real",
+  "cess",
+  "nds",
+  "▁big",
+  "▁num",
+  "ction",
+  "▁add",
+  "▁set",
+  "▁um",
+  "ood",
+  "ible",
+  "▁own",
+  "▁life",
+  "ities",
+  "▁its",
+  "▁God",
+  "pect",
+  "▁didn",
+  "stem",
+  "les",
+  "uc",
+  "ib",
+  "ating",
+  "olog",
+  "▁person",
+  "▁inv",
+  "ably",
+  "▁sure",
+  "▁reg",
+  "lic",
+  "▁stu",
+  "▁cr",
+  "▁ev",
+  "ments",
+  "▁another",
+  "▁la",
+  "▁last",
+  "▁sub",
+  "▁att",
+  "▁op",
+  "▁inst",
+  "▁sl",
+  "▁happen",
+  "▁rep",
+  "▁import",
+  "ific",
+  "ix",
+  "▁made",
+  "▁ear",
+  "▁ac",
+  "▁def",
+  "ute",
+  "▁next",
+  "ative",
+  "▁form",
+  "▁guys",
+  "▁system",
+  "ew",
+  "▁able",
+  "ied",
+  "▁always",
+  "ren",
+  "erest",
+  "▁As",
+  "▁mod",
+  "▁done",
+  "ings",
+  "▁love",
+  "ism",
+  "▁ask",
+  "old",
+  "ered",
+  "▁trans",
+  "▁count",
+  "ility",
+  "▁high",
+  "▁fin",
+  "▁prob",
+  "▁pol",
+  "▁exam",
+  "▁pres",
+  "▁maybe",
+  "ell",
+  "▁stud",
+  "▁prod",
+  "▁car",
+  "ock",
+  "▁used",
+  "oy",
+  "stand",
+  "▁No",
+  "▁mon",
+  "ks",
+  "▁interest",
+  "▁ent",
+  "ited",
+  "▁sort",
+  "▁For",
+  "▁today",
+  "ics",
+  "▁vide",
+  "▁bec",
+  "▁Well",
+  "▁Al",
+  "▁important",
+  "▁such",
+  "▁run",
+  "▁keep",
+  "▁fact",
+  "ata",
+  "ss",
+  "▁never",
+  "ween",
+  "▁stuff",
+  "ract",
+  "▁question",
+  "als",
+  "▁sim",
+  "vern",
+  "ather",
+  "▁course",
+  "▁Of",
+  "oc",
+  "ness",
+  "arch",
+  "ize",
+  "▁All",
+  "ense",
+  "blem",
+  "▁probably",
+  "hip",
+  "▁number",
+  "ention",
+  "▁saying",
+  "▁commun",
+  "▁An",
+  "akes",
+  "▁belie",
+  "▁between",
+  "▁better",
+  "cus",
+  "▁place",
+  "▁gener",
+  "▁ca",
+  "▁ins",
+  "▁ass",
+  "cond",
+  "cept",
+  "ull",
+  "▁understand",
+  "▁fun",
+  "▁thought",
+  "gan",
+  "iew",
+  "cy",
+  "ution",
+  "ope",
+  "ason",
+  "▁problem",
+  "▁doesn",
+  "ational",
+  "▁read",
+  "▁trying",
+  "▁sch",
+  "▁el",
+  "ah",
+  "atter",
+  "▁exper",
+  "▁four",
+  "▁ele",
+  "▁cou",
+  "ont",
+  "▁called",
+  "▁partic",
+  "▁open",
+  "▁gl",
+  "▁everything",
+  "▁eff",
+  "▁getting",
+  "▁ty",
+  "▁Am",
+  "▁Because",
+  "ave",
+  "▁met",
+  "▁Like",
+  "oney",
+  "▁",
+  "e",
+  "t",
+  "o",
+  "a",
+  "n",
+  "i",
+  "s",
+  "h",
+  "r",
+  "l",
+  "d",
+  "u",
+  "c",
+  "y",
+  "m",
+  "g",
+  "w",
+  "f",
+  "p",
+  ",",
+  "b",
+  ".",
+  "k",
+  "v",
+  "'",
+  "I",
+  "T",
+  "A",
+  "S",
+  "j",
+  "x",
+  "W",
+  "B",
+  "C",
+  "?",
+  "0",
+  "O",
+  "-",
+  "M",
+  "H",
+  "Y",
+  "q",
+  "1",
+  "P",
+  "z",
+  "L",
+  "D",
+  "N",
+  "G",
+  "F",
+  "R",
+  "E",
+  "2",
+  "J",
+  "U",
+  ":",
+  "5",
+  "9",
+  "3",
+  "K",
+  "4",
+  "V",
+  "8",
+  "6",
+  "7",
+  "!",
+  "%",
+  "Q",
+  "$",
+  "Z",
+  "X",
+  "é",
+  "/",
+  "í",
+  "á",
+  "£",
+  "ó",
+  "ā",
+  "ü",
+  "ñ",
+  "ö",
+  "è",
+  "ç",
+  "à",
+  "¿",
+  "μ",
+  "π",
+  "ä",
+  "ú",
+  "θ",
+  "ã",
+  "φ",
+  "ī",
+  "σ",
+  "ê",
+  "ρ",
+  "â",
+  "ô",
+  "^",
+  "€",
+  "É",
+  "ū",
+  "Δ",
+  "λ",
+  "α",
+  "τ",
+  "æ",
+  "а",
+  "о",
+  "ν",
+  "î",
+  "γ",
+  "ψ",
+  "ē",
+  "т",
+  "ß",
+  "ω",
+  "ï",
+  "ć",
+  "č",
+  "ε",
+  "е",
+  "и",
+  "ò",
+  "р",
+  "β",
+  "ø",
+  "ł",
+  "δ",
+  "η",
+  "п",
+  "ë",
+  "н",
+  "с",
+  "š",
+  "Ü",
+  "å",
+  "ń",
+  "ś",
+  "я",
+  "đ",
+  "л",
+  "м",
+  "Ö",
+  "û",
+  "ș",
+  "в",
+  "Á",
+  "Ø",
+  "ù",
+  "ο",
+  "ч",
+  "ь",
+  "ž",
+  "Φ",
+  "у",
+  "ę",
+  "ι",
+  "б",
+  "г",
+  "к",
+  "ő",
+  "Ś",
+  "Ω",
+  "κ",
+  "υ",
+  "ì",
+  "Č",
+  "έ",
+  "х",
+  "ы",
+  "Å",
+  "Ç",
+  "ż",
+  "ί",
+  "ζ",
+  "χ",
+  "э",
+  "Æ",
+  "Í",
+  "õ",
+  "ě",
+  "ħ",
+  "Ł",
+  "œ",
+  "Ž",
+  "ț",
+  "Γ",
+  "П",
+  "д",
+  "з",
+  "ф",
+  "¡",
+  "À",
+  "Î",
+  "Ā",
+  "ė",
+  "Š",
+  "ź",
+  "Κ",
+  "Ψ",
+  "ά",
+  "ξ",
+  "ό"
+]