ModelPublicadoExterno

Gigaam v3 Rnnt Coreml

This is a Core ML conversion of v3rnnt from ai-sage/GigaAM-v3. It contains separate encoder, predictor, and joiner ML Programs.

Fuentehuggingface.co/vadimsuhanov/gigaam-v3-rnnt-coreml/tree/6a8eb79f7f72e5b3b615d4f7b722ac1297532248

TipoOtherModelo baseai-sage/GigaAM-v3VersiónRevision 6a8eb79Bcalidad

Fuente del modelo

Tipo: Other
Tamaño del archivo: 1,37–842 MB
Modelo base: ai-sage/GigaAM-v3
Versión: vRevision 6a8eb79
Actualizado: 31 oct 2026
Descargas: 8
Fuente: Hugging Face

Descripción de la fuente

GigaAM v3_rnnt Core ML staged artifact

This is a Core ML conversion of v3_rnnt from ai-sage/GigaAM-v3. It contains separate encoder, predictor, and joiner ML Programs.

Provenance

repository: https://github.com/salute-developers/GigaAM
revision: 559d88d6b72541412743929f633a6ae7c9950b85
variant: v3_rnnt

Conversion precision: float32
Upstream license: MIT

Runtime contract

The artifact uses fixed batch-one Core ML inputs for Russian audio of at most 25 seconds. See model-config.json and conversion-manifest.json for the exact tensor and checksum contracts.

This staged artifact must pass its parity validation before publication.

Fuentes

1 fuente

Hugging FacePrincipalVersión 6a8eb79f7f72e5b3b615d4f7b722ac1297532248

huggingface.co/vadimsuhanov/gigaam-v3-rnnt-coreml/tree/6a8eb79f7f72e5b3b615d4f7b722ac1297532248

Verificado 31 oct

Download files

Repository files

File inventory only; completeness is unverified.

Artefactos del modelo

3 artefactos

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

bin · 842 MB · SHA-256 36c0c9c11f4e…940e · Hugging Face

Download file

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

bin · 1,37 MB · SHA-256 86aa5a2ee3c0…d873 · Hugging Face

Download file

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

bin · 3,17 MB · SHA-256 dac169601fdf…1dbe · Hugging Face

Download file

Extractos de fuentes

3 extractos

Readme15 agohuggingface.co/vadimsuhanov/gigaam-v3-rnnt-coreml

--- license: mit language: - ru pipeline_tag: automatic-speech-recognition library_name: coreml base_model: ai-sage/GigaAM-v3 tags: - coreml - gigaam - speech-recognition - macos - rnnt - v3_rnnt --- # GigaAM v3_rnnt Core ML staged artifact This is a Core ML conversion of `v3_rnnt` from [ai-sage/GigaAM-v3](https://huggingface.co/ai-sage/GigaAM-v3). It contains separate encoder, predictor, and joiner ML Programs. ## Provenance ```yaml repository: https://github.com/salute-developers/GigaAM revision: 559d88d6b72541412743929f633a6ae7c9950b85 variant: v3_rnnt ``` - Conversion precision: `float32` - Upstream license: `MIT` ## Runtime contract The artifact uses fixed batch-one Core ML inputs for Russian audio of at most 25 seconds. See `model-config.json` and `conversion-manifest.json` for the exact tensor and checksum contracts. This staged artifact must pass its parity validation before publication.

Note31 octhuggingface.co/vadimsuhanov/gigaam-v3-rnnt-coreml

Source context: 8 downloads · 0 likes · Pipeline automatic-speech-recognition · Library coreml · Repo vadimsuhanov/gigaam-v3-rnnt-coreml

Note15 agohuggingface.co/vadimsuhanov/gigaam-v3-rnnt-coreml

Source context: 6 downloads · 0 likes · Pipeline automatic-speech-recognition · Library coreml · Repo vadimsuhanov/gigaam-v3-rnnt-coreml