Mirror of mlboydaisuke/Parakeet-TDT-0.6B-CoreAI

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* 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
+parakeet_encoder_float16_L2885.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
+parakeet_joint_float32.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
+parakeet_predict_float32.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
+demo.gif filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,80 @@
+---
+license: cc-by-4.0
+library_name: coreai
+pipeline_tag: automatic-speech-recognition
+base_model: nvidia/parakeet-tdt-0.6b-v3
+tags: [core-ai, coreaikit, parakeet, tdt, rnn-t, transducer, asr, on-device, apple]
+---
+
+> **Mirror** of [`mlboydaisuke/Parakeet-TDT-0.6B-CoreAI`](https://huggingface.co/mlboydaisuke/Parakeet-TDT-0.6B-CoreAI) — the canonical repo ([CoreAI Model Zoo](https://github.com/john-rocky/coreai-model-zoo)). Updates land there first.
+
+
+# Parakeet-TDT-0.6B — Core AI
+
+[`nvidia/parakeet-tdt-0.6b-v3`](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) (cc-by-4.0, 600M)
+converted to **Apple Core AI** `.aimodel` — the first **transducer / TDT (RNN-T family)** ASR in the
+[zoo](https://github.com/john-rocky/coreai-models-community). Transcribes ≤~29 s clips in 25
+European languages as **three stateless graphs + a host greedy loop** (no LLM runtime).
+
+- `parakeet_encoder_float16_L2885.aimodel` — FastConformer encoder + projector (fp16, ~1.2 GB),
+  `mel[1,128,2885] → enc_proj[1,361,640]`.
+- `parakeet_predict_float32.aimodel` — embedding → 2-layer LSTM → projector (fp32),
+  `token[1,1],h,c[2,1,640] → dec_out[1,640],h',c'`.
+- `parakeet_joint_float32.aimodel` — `head(relu(enc_frame+dec_out))` (fp32),
+  `→ token_logits[1,8193], dur_logits[1,5]`.
+- `tokenizer.json` (+ `tokenizer_config.json`), `mel_filters_128x257_f32.bin` (librosa-slaney).
+
+Gated **77/77 token-exact** end-to-end vs the HF `ParakeetForTDT` reference, and again token-exact
+through the Swift **CoreAIKit** `KitParakeetModel`. blank 8192 · durations [0,1,2,3,4] · 16 kHz.
+
+<!-- gen-cards:use-it begin id=parakeet-tdt-0.6b-v3 (managed by scripts/gen-cards — edit cards.json / QuickStart.swift, not this block) -->
+![Parakeet-TDT 0.6B v3 demo](https://huggingface.co/mlboydaisuke/Parakeet-TDT-0.6B-CoreAI/resolve/main/demo.gif)
+*Parakeet-TDT 0.6B on iPhone 17 Pro — the zoo's coreai-audio app, real speed.*
+
+## Use it
+
+▶️ **Run it (source)** — the [Transcribe runner](https://github.com/john-rocky/coreai-kit/tree/main/Examples/Transcribe)
+(GUI + CLI, one app for every speech-to-text model in the catalog):
+
+```bash
+git clone https://github.com/john-rocky/coreai-kit
+open coreai-kit/Examples/Transcribe/Transcribe.xcodeproj
+# → Run, then pick "Parakeet-TDT 0.6B v3" in the model picker
+
+# agents / headless (macOS):
+cd coreai-kit/Examples/Transcribe
+swift run transcribe-cli --model parakeet-tdt-0.6b-v3 --audio sample.wav
+```
+
+💻 **Build with it** — complete; the glue is kit API, copy-paste runs:
+
+```swift
+import CoreAIKit
+
+let transcriber = try await KitTranscriber(catalog: "parakeet-tdt-0.6b-v3")
+let samples = try AudioFile.pcm16kMono(url)  // any wav/m4a/mp3 → 16 kHz mono Float
+let result = try await transcriber.transcribe(samples: samples)
+// result.text (25 EU languages)
+```
+
+The take-home is [`Examples/Transcribe/Sources/QuickStart.swift`](https://github.com/john-rocky/coreai-kit/blob/main/Examples/Transcribe/Sources/QuickStart.swift)
+— this exact code as one typed function, no UI; both the runner's GUI and its CLI call it.
+Recording? `MicRecorder` (kit API) captures mic audio as 16 kHz mono `[Float]` — the record
+button and permission prompt are your app's own chrome.
+
+**Integration checklist**
+
+- SPM: `https://github.com/john-rocky/coreai-kit` → product **CoreAIKit**
+- Info.plist: `NSMicrophoneUsageDescription` — only if you record
+- Entitlements: none needed (macOS)
+- First run downloads the model — 1.3 GB (Mac) — then it loads from the
+  local cache (Application Support; progress via the `downloadProgress` callback)
+- Measure in Release — Debug is ~3× slower on per-token host work
+<!-- gen-cards:use-it end -->
+
+## Use (CoreAIKit)
+
+```swift
+let parakeet = try await KitParakeetModel(model: .parakeetTDT)
+let result = try await parakeet.transcribe(samples: pcm16kMono)   // 16 kHz mono Float
+```

mel_filters_128x257_f32.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bce5ec5f194a5913f6508cee5a85512e7bad2352db8fc28f5c6ff75af8b09137
+size 131584

parakeet_encoder_float16_L2885.aimodel/main.hash

@@ -0,0 +1 @@
+P�Q)�{.�x�ШQX1�mE��@�`��q�.�(

parakeet_encoder_float16_L2885.aimodel/main.mlirb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509e5129f87b2e8d78cdd0a85158311eb36d45b78b409d60f7fb71ae2e02ef28
+size 1221023465

parakeet_encoder_float16_L2885.aimodel/metadata.json

@@ -0,0 +1,4 @@
+{
+  "assetVersion" : "2.0",
+  "license" : "cc-by-4.0"
+}

parakeet_joint_float32.aimodel/main.hash

@@ -0,0 +1 @@
+�m3p��QW�&%��>��1K���_�N�>���

parakeet_joint_float32.aimodel/main.mlirb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a26d337099b65157eb2602258ce79a3ea8b3314be41188eb5f8a4ee03e889afd
+size 21021917

parakeet_joint_float32.aimodel/metadata.json

@@ -0,0 +1,4 @@
+{
+  "assetVersion" : "2.0",
+  "license" : "cc-by-4.0"
+}

parakeet_predict_float32.aimodel/main.hash

@@ -0,0 +1 @@
+���A��e8œMlږ,�����U

parakeet_predict_float32.aimodel/main.mlirb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e80bebf441ad9b650f38c5934d6cda962cf884fa8995550dd384253f1ef4ebcb
+size 48880540

parakeet_predict_float32.aimodel/metadata.json

@@ -0,0 +1,4 @@
+{
+  "assetVersion" : "2.0",
+  "license" : "cc-by-4.0"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "ParakeetProcessor",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": "<unk>"
+}