parakeet is an open-weight model from Volantis Labs, released under Creative Commons Attribution 4.0. Its published files total 529.3 MB. It draws 43 downloads a month.
Speech recognition: Parakeet TDT 0.6B v3 with ternary encoder weights, as a Core ML model set and an ONNX model set.
Model Card
By Volantis Labs, published under cc-by-4.0, revision 581cfb995257.
Speech recognition: Parakeet TDT 0.6B v3 with ternary encoder weights, as a Core ML model set and an ONNX model set. - coreml/: Core ML compiled models (Preprocessor, Encoder with 2-bit weights, Decoder, JointDecision; the joint also returns its float32 logits), with config.json, tokens.txt and SHA256SUMS. macOS 15 or later. - onnx/: ONNX encoder (2-bit MatMulNBits), decoder, joiner and voice activity model, with config.json, tokens.txt and SHA256SUMS. Core ML model set on the GPU, on a 62.9-minute subset of the AMI meeting corpus: 22.49% word error rate, about 126x real time on an Apple M3 Max.
Read Volantis Labs's full model card
Parakeet TDT 0.6B v3, ternary (Core ML and ONNX)
Speech recognition: Parakeet TDT 0.6B v3 with ternary encoder weights, as a Core ML model set and an ONNX model set.
- Credit: NVIDIA, parakeet-tdt-0.6b-v3. Moondream, Parakeet Redux ternary weights. Redistributed under CC BY 4.0.
Layout
coreml/: Core ML compiled models (Preprocessor, Encoder with 2-bit weights, Decoder, JointDecision; the joint also returns its float32 logits), withconfig.json,tokens.txtandSHA256SUMS. macOS 15 or later.onnx/: ONNX encoder (2-bit MatMulNBits), decoder, joiner and voice activity model, withconfig.json,tokens.txtandSHA256SUMS.
Measured accuracy and speed
Core ML model set on the GPU, on a 62.9-minute subset of the AMI meeting corpus: 22.49% word error rate, about 126x real time on an Apple M3 Max.
Files
| File | Bytes | SHA-256 |
|---|---|---|
config.json |
119 | 8a8d7725b0bb3127eef2168a42c797b97a29adee4f1c0879dd04597dc1871094 |
coreml/Decoder.mlmodelc/analytics/coremldata.bin |
243 | f5c3836cf3c871317e6240a47726f3a866bbafa07c58d9d89fb8b675c71a116b |
coreml/Decoder.mlmodelc/coremldata.bin |
636 | 61ab80717a58bc216aec2f5baf1f2ff6420341c725597d2972174fc9b77183da |
coreml/Decoder.mlmodelc/metadata.json |
3223 | 1881f965785e90ca4c0ed964559bd9f3455b7d5f6140e970e6f4f01c0e032124 |
coreml/Decoder.mlmodelc/model.mil |
11543 | 85543f13c2a8cc545854d4ddeb377fb3dc871655e2d32e5820b5adfbfcedd559 |
coreml/Decoder.mlmodelc/weights/weight.bin |
23604992 | 6c6c88c23ee5492a6b229e8cc636ddadb2b01ae0dd559d9cb63123bebf507d77 |
coreml/Encoder.mlmodelc/analytics/coremldata.bin |
243 | e1d91863f0931d56db3fba0b6e7e5d638f78538d61182a06a01c512b132c19c6 |
coreml/Encoder.mlmodelc/coremldata.bin |
542 | c158fd6bd0d47907f839ef8bc0c1c0fb39f520eedaa0a6a8eb698f867cbff59a |
coreml/Encoder.mlmodelc/metadata.json |
2746 | 32802d3d067d216f9926c5f69b1f232c8223912ac2df735f90346b84dd89132b |
coreml/Encoder.mlmodelc/model.mil |
598228 | 4382aeb884dfe5a26566d8080136346ac7e27d9ee754989d5d845a5ac45145fe |
coreml/Encoder.mlmodelc/weights/weight.bin |
209137408 | b1bc0a0d9d3cb333bfa94d2c61723a9e3729232f6548c25b6c9c8cc80cc2f845 |
coreml/JointDecision.mlmodelc/analytics/coremldata.bin |
243 | 270d341e5556d87f2c543a985c9699746a36c5dd28871b23c06ce5f5746d8468 |
coreml/JointDecision.mlmodelc/coremldata.bin |
674 | 96292706af43c9f82de1f60b89745795002bea197ca6068aa8020cb960158060 |
coreml/JointDecision.mlmodelc/metadata.json |
2870 | 0170b87d3fd9ad2ef4b015f5c760d2a7bc75fb4e9c5c4c5652eb7cfc6d892db4 |
coreml/JointDecision.mlmodelc/model.mil |
7389 | dea37f050422d644a8fbc2b44be8bd253130e00f651742a9a8f7996c7e749e76 |
coreml/JointDecision.mlmodelc/weights/weight.bin |
12642764 | 73b0288acd115fc4c36038f66b6cbf49233182488febf5d8c787bea4009535f7 |
coreml/Preprocessor.mlmodelc/analytics/coremldata.bin |
243 | 22a1be9d0a96c322b682a5266c7991eaa2ee64ac4ef461a14c6d685dcc349ec6 |
coreml/Preprocessor.mlmodelc/coremldata.bin |
634 | 5fba267149d02c1f3a38f8c0d56ba4dda575325850b52734921e1280bee78f26 |
coreml/Preprocessor.mlmodelc/metadata.json |
2788 | 71064c5b04bc31737dd0c142dc82f4f53d64884072aaba5530675645eec90283 |
coreml/Preprocessor.mlmodelc/model.mil |
11174 | 2e12d640d5c631261b9e632c458ba347153dd1dfe81a91c24b4cfc0e2c3e423b |
coreml/Preprocessor.mlmodelc/weights/weight.bin |
2150592 | 25b7de10562b2f6b51b976e1c23de4edc80cbcd6517d4d20d0205e706b4fd41a |
coreml/SHA256SUMS |
2202 | f343c347cb6e48b8182a2680ede90eb09fe8bfccfb8585f9dbd72f3375aaf5fa |
coreml/config.json |
4127 | 10289a3c359d2733b3f1468cfafd396da703a63925dc6d7e910dd500bc7d7982 |
coreml/tokens.txt |
93939 | d58544679ea4bc6ac563d1f545eb7d474bd6cfa467f0a6e2c1dc1c7d37e3c35d |
onnx/SHA256SUMS |
466 | 368204bf6425ea4e227226b83325aa2ea5a1aecda2e208f8dc3be763cb3084e8 |
onnx/config.json |
2386 | 9536176118bd2fc02ffadc7f47de2ef8e98c1efd08121287a514f77feeb7bb87 |
onnx/decoder.onnx |
47232960 | 3316e0084531cdbd11e2b0fe0c7a310283756ab9fec1e56f3a2b64f4f8db40c4 |
onnx/encoder.onnx |
190236080 | 62d21bcce08681809ce0378ec6969fc03b7baa6c54e7d7ab161ed5b20dbba12e |
onnx/joiner.onnx |
25286284 | a144eafbe6209bbd8f1144197d195e96f7d742611f546100776f961a31bd3513 |
onnx/tokens.txt |
93939 | d58544679ea4bc6ac563d1f545eb7d474bd6cfa467f0a6e2c1dc1c7d37e3c35d |
onnx/vad.onnx |
18209377 | cf9fd348d454d16ccaf3a7474717d9054fb2be88b9b310f36854f66433d34c24 |
Configuration
- Model type
- parakeet-tdt-0.6b-v3-ternary
Identity and Version
- Repository
- volantis-labs/parakeet
- Publisher
- Volantis Labs
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 581cfb995257c6041b7f883f74214fb8423f00ed
- First published
- 2026-09-24
- Last updated
- 2026-10-16
Files and Weights
33 files, 529.3 MB in total. The weights are 16 files totalling 528.5 MB in bin, onnx.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| coreml/Decoder.mlmodelc/analytics/coremldata.bin | Weights | 243 B | f5c3836cf3c8 |
| coreml/Decoder.mlmodelc/coremldata.bin | Weights | 636 B | 61ab80717a58 |
| coreml/Decoder.mlmodelc/weights/weight.bin | Weights | 23.6 MB | 6c6c88c23ee5 |
| coreml/Encoder.mlmodelc/analytics/coremldata.bin | Weights | 243 B | e1d91863f093 |
| coreml/Encoder.mlmodelc/coremldata.bin | Weights | 542 B | c158fd6bd0d4 |
| coreml/Encoder.mlmodelc/weights/weight.bin | Weights | 209.1 MB | b1bc0a0d9d3c |
| coreml/JointDecision.mlmodelc/analytics/coremldata.bin | Weights | 243 B | 270d341e5556 |
| coreml/JointDecision.mlmodelc/coremldata.bin | Weights | 674 B | 96292706af43 |
| coreml/JointDecision.mlmodelc/weights/weight.bin | Weights | 12.6 MB | 73b0288acd11 |
| coreml/Preprocessor.mlmodelc/analytics/coremldata.bin | Weights | 243 B | 22a1be9d0a96 |
| coreml/Preprocessor.mlmodelc/coremldata.bin | Weights | 634 B | 5fba267149d0 |
| coreml/Preprocessor.mlmodelc/weights/weight.bin | Weights | 2.2 MB | 25b7de10562b |
| onnx/decoder.onnx | Weights | 47.2 MB | 3316e0084531 |
| onnx/encoder.onnx | Weights | 190.2 MB | 62d21bcce086 |
| onnx/joiner.onnx | Weights | 25.3 MB | a144eafbe620 |
| onnx/vad.onnx | Weights | 18.2 MB | cf9fd348d454 |
| config.json | Configuration | 119 B | — |
| coreml/Decoder.mlmodelc/metadata.json | Configuration | 3.2 KB | — |
| coreml/Encoder.mlmodelc/metadata.json | Configuration | 2.7 KB | — |
| coreml/JointDecision.mlmodelc/metadata.json | Configuration | 2.9 KB | — |
| coreml/Preprocessor.mlmodelc/metadata.json | Configuration | 2.8 KB | — |
| coreml/config.json | Configuration | 4.1 KB | — |
| onnx/config.json | Configuration | 2.4 KB | — |
| README.md | Documentation | 4.5 KB | — |
| coreml/Decoder.mlmodelc/model.mil | Other | 11.5 KB | — |
| coreml/Encoder.mlmodelc/model.mil | Other | 598.2 KB | — |
| coreml/JointDecision.mlmodelc/model.mil | Other | 7.4 KB | — |
| coreml/Preprocessor.mlmodelc/model.mil | Other | 11.2 KB | — |
| coreml/SHA256SUMS | Other | 2.2 KB | — |
| coreml/tokens.txt | Other | 93.9 KB | — |
| onnx/SHA256SUMS | Other | 466 B | — |
| onnx/tokens.txt | Other | 93.9 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- cc-by-4.0
- Access
- Open weights, no gate
- Download size
- 528.5 MB
Released by Volantis Labs through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 528.5 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About parakeet
Can I use parakeet commercially?
Yes. parakeet is released under Creative Commons Attribution 4.0. CC BY 4.0 permits sharing and adapting the work, including commercially, provided the creator is credited and changes are indicated.