Skip to content

Commit 00d2236

Browse files
hanbitmythshanbitmyths
authored
Add parakeet model into Foundry Local (#5094)
1 parent 57b302b commit 00d2236

12 files changed

Lines changed: 147 additions & 0 deletions

File tree

‎assets/models/foundrylocal/parakeet-tdt-0.6b-v2-cuda-gpu/asset.yaml‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,4 @@
1+
extra_config: model.yaml
2+
spec: spec.yaml
3+
type: model
4+
categories: ["Local"]

‎assets/models/foundrylocal/parakeet-tdt-0.6b-v2-cuda-gpu/description.md‎

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,11 @@
1+
This model is an optimized version of parakeet-tdt-0.6b-v2 for local inference on CUDA GPUs. This optimized model is published here in ONNX format to run on CUDA-capable GPU devices, with the precision best suited to this target.
2+
3+
# Model Description
4+
- **Developed by:** Microsoft
5+
- **Model type:** ONNX
6+
- **License:** MIT
7+
- **Model Description:** This is a conversion of the parakeet-tdt-0.6b-v2 for local inference.
8+
- **Disclaimer:** Model is only an optimization of the base model, any risk associated with the model is the responsibility of the user of the model. Please verify and test for your scenarios. There may be a slight difference in output from the base model with the optimizations applied. Note that optimizations applied are distinct from fine tuning and thus do not alter the intended uses or capabilities of the model.
9+
10+
# Base Model Information
11+
See Hugging Face model [parakeet-tdt-0.6b-v2](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2) for details.

‎assets/models/foundrylocal/parakeet-tdt-0.6b-v2-cuda-gpu/model.yaml‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
path:
2+
container_name: models
3+
container_path: foundrylocal/models/parakeet-tdt-0.6b-v2/onnx/cuda/v1
4+
storage_name: foundrylocalassetdata
5+
type: azureblob
6+
publish:
7+
description: description.md
8+
type: custom_model

‎assets/models/foundrylocal/parakeet-tdt-0.6b-v2-cuda-gpu/spec.yaml‎

Lines changed: 35 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,35 @@
1+
$schema: https://azuremlschemas.azureedge.net/latest/model.schema.json
2+
name: parakeet-tdt-0.6b-v2-cuda-gpu
3+
version: 1
4+
isArchived: true
5+
path: ./
6+
tags:
7+
foundryLocal: "test"
8+
license: "MIT"
9+
licenseDescription: "This model is provided under the License Terms available at <https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2#licenseterms-of-use>."
10+
author: Microsoft
11+
inputModalities: "audio"
12+
outputModalities: "text"
13+
task: automatic-speech-recognition
14+
maxOutputTokens: 2048
15+
alias: parakeet-tdt-0.6b-v2
16+
directoryPath: v1
17+
promptTemplate: ""
18+
capabilities: ""
19+
supportsReasoning: ""
20+
reasoningStart: ""
21+
reasoningEnd: ""
22+
contextLength: 0
23+
minFLVersion: "1.2.0"
24+
disable-maap: "true"
25+
type: custom_model
26+
variantInfo:
27+
parents:
28+
- assetId: azureml://registries/azureml/models/parakeet-tdt-0.6b-v2/versions/1
29+
variantMetadata:
30+
modelType: 'ONNX'
31+
quantization: ['RTN']
32+
device: 'gpu'
33+
executionProvider: 'CUDAExecutionProvider'
34+
fileSizeBytes: 725652848
35+
vRamFootprintBytes: 725652848

‎assets/models/foundrylocal/parakeet-tdt-0.6b-v2-generic-cpu/asset.yaml‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,4 @@
1+
extra_config: model.yaml
2+
spec: spec.yaml
3+
type: model
4+
categories: ["Local"]

‎assets/models/foundrylocal/parakeet-tdt-0.6b-v2-generic-cpu/description.md‎

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,11 @@
1+
This model is an optimized version of parakeet-tdt-0.6b-v2 for local inference. Optimized models are published here in ONNX format to run on CPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs.
2+
3+
# Model Description
4+
- **Developed by:** Microsoft
5+
- **Model type:** ONNX
6+
- **License:** MIT
7+
- **Model Description:** This is a conversion of the parakeet-tdt-0.6b-v2 for local inference.
8+
- **Disclaimer:** Model is only an optimization of the base model, any risk associated with the model is the responsibility of the user of the model. Please verify and test for your scenarios. There may be a slight difference in output from the base model with the optimizations applied. Note that optimizations applied are distinct from fine tuning and thus do not alter the intended uses or capabilities of the model.
9+
10+
# Base Model Information
11+
See Hugging Face model [parakeet-tdt-0.6b-v2](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2) for details.

‎assets/models/foundrylocal/parakeet-tdt-0.6b-v2-generic-cpu/model.yaml‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
path:
2+
container_name: models
3+
container_path: foundrylocal/models/parakeet-tdt-0.6b-v2/onnx/cpu_and_mobile/v1
4+
storage_name: foundrylocalassetdata
5+
type: azureblob
6+
publish:
7+
description: description.md
8+
type: custom_model

‎assets/models/foundrylocal/parakeet-tdt-0.6b-v2-generic-cpu/spec.yaml‎

Lines changed: 35 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,35 @@
1+
$schema: https://azuremlschemas.azureedge.net/latest/model.schema.json
2+
name: parakeet-tdt-0.6b-v2-generic-cpu
3+
version: 1
4+
isArchived: true
5+
path: ./
6+
tags:
7+
foundryLocal: "test"
8+
license: "MIT"
9+
licenseDescription: "This model is provided under the License Terms available at <https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2#licenseterms-of-use>."
10+
author: Microsoft
11+
inputModalities: "audio"
12+
outputModalities: "text"
13+
task: automatic-speech-recognition
14+
maxOutputTokens: 2048
15+
alias: parakeet-tdt-0.6b-v2
16+
directoryPath: v1
17+
promptTemplate: ""
18+
capabilities: ""
19+
supportsReasoning: ""
20+
reasoningStart: ""
21+
reasoningEnd: ""
22+
contextLength: 0
23+
minFLVersion: "1.2.0"
24+
disable-maap: "true"
25+
type: custom_model
26+
variantInfo:
27+
parents:
28+
- assetId: azureml://registries/azureml/models/parakeet-tdt-0.6b-v2/versions/1
29+
variantMetadata:
30+
modelType: 'ONNX'
31+
quantization: ['RTN']
32+
device: 'cpu'
33+
executionProvider: 'CPUExecutionProvider'
34+
fileSizeBytes: 725652479
35+
vRamFootprintBytes: 725652479

‎assets/models/foundrylocal/parakeet-tdt-0.6b-v2/asset.yaml‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,4 @@
1+
extra_config: model.yaml
2+
spec: spec.yaml
3+
type: model
4+
categories: ["Local"]

‎assets/models/foundrylocal/parakeet-tdt-0.6b-v2/description.md‎

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,11 @@
1+
This model is an optimized version of parakeet-tdt-0.6b-v2 for local inference. Optimized models are published here in ONNX format to run on CPU and CUDA GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs.
2+
3+
# Model Description
4+
- **Developed by:** Microsoft
5+
- **Model type:** ONNX
6+
- **License:** MIT
7+
- **Model Description:** This is a conversion of the parakeet-tdt-0.6b-v2 for local inference.
8+
- **Disclaimer:** Model is only an optimization of the base model, any risk associated with the model is the responsibility of the user of the model. Please verify and test for your scenarios. There may be a slight difference in output from the base model with the optimizations applied. Note that optimizations applied are distinct from fine tuning and thus do not alter the intended uses or capabilities of the model.
9+
10+
# Base Model Information
11+
See Hugging Face model [parakeet-tdt-0.6b-v2](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2) for details.

0 commit comments

Comments
 (0)