Text Generation
LiteRT-LM
LiteRT
English
litertlm
on-device
edge
asr
automatic-speech-recognition
text-normalization
inverse-text-normalization
punctuation
truecasing
speech-to-text
dictation
post-processing
qwen3
Instructions to use mlboydaisuke/S1-mini-LiteRT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use mlboydaisuke/S1-mini-LiteRT with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli litert-lm run \ --from-huggingface-repo=mlboydaisuke/S1-mini-LiteRT \ --prompt="Write me a poem"
- LiteRT
How to use mlboydaisuke/S1-mini-LiteRT 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
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -96,9 +96,9 @@ iPhone 17 Pro, single 180-token prompt, cold start:
|
|
| 96 |
| Backend | Prefill | Decode | TTFT | Peak memory |
|
| 97 |
|---|---|---|---|---|
|
| 98 |
| GPU (Metal) | 768–801 tok/s | 32.0 tok/s | 0.31 s | 1.7 GB |
|
| 99 |
-
| CPU | 281 tok/s | 15.5 tok/s | 0.74 s |
|
| 100 |
|
| 101 |
-
|
| 102 |
|
| 103 |
In practice a short dictation turn — one or two sentences in, one or two out — completes in about 3 seconds on a Pixel 8a CPU.
|
| 104 |
|
|
|
|
| 96 |
| Backend | Prefill | Decode | TTFT | Peak memory |
|
| 97 |
|---|---|---|---|---|
|
| 98 |
| GPU (Metal) | 768–801 tok/s | 32.0 tok/s | 0.31 s | 1.7 GB |
|
| 99 |
+
| CPU | 281 tok/s | 15.5 tok/s | 0.74 s | 1.4 GB |
|
| 100 |
|
| 101 |
+
Every iPhone run above was recorded with the device reporting a `serious` thermal state, so read them as floors rather than peaks. The Metal row is the pair of runs that agreed (32.02 and 32.01 tok/s); an earlier Metal run of the same build read 30.2 tok/s.
|
| 102 |
|
| 103 |
In practice a short dictation turn — one or two sentences in, one or two out — completes in about 3 seconds on a Pixel 8a CPU.
|
| 104 |
|