Automatic Speech Recognition
WhisperKit
LiteRT
LiteRT
whisper
parakeet
nvidia
openai
asr
transcription
local
on-device
quantized
compressed
Instructions to use argmaxinc/parakeetkit-litert-pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- WhisperKit
How to use argmaxinc/parakeetkit-litert-pro with WhisperKit:
# Install CLI with Homebrew on macOS device brew install whisperkit-cli # View all available inference options whisperkit-cli transcribe --help # Download and run inference using whisper base model whisperkit-cli transcribe --audio-path /path/to/audio.mp3 # Or use your preferred model variant whisperkit-cli transcribe --model "large-v3" --model-prefix "distil" --audio-path /path/to/audio.mp3 --verbose
- LiteRT
How to use argmaxinc/parakeetkit-litert-pro with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Update Parakeet-v3 AudioEncoder asset for G3 and G4 chips
Browse filesUpdate Parakeet-v3 AudioEncoder asset for G3 and G4 chips.
parakeet-tdt-0.6b-v3/QuantAudioEncoder.aipack/src/main/assets/model#group_Google_Tensor_G3/AudioEncoder.tflite
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:309ddecd8cfc47b6e31df2f161d754bf77d17fdfe165d28708245dfd4a9aed69
|
| 3 |
+
size 843097920
|
parakeet-tdt-0.6b-v3/QuantAudioEncoder.aipack/src/main/assets/model#group_Google_Tensor_G4/AudioEncoder.tflite
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ed2aef772e1c41d908a10056f1a54722163442e15b57e3bd7d18fa99088268e
|
| 3 |
+
size 843097920
|