Card: measured device / browser results (edge-compat, 2026-09)
Browse files
README.md
CHANGED
|
@@ -25,6 +25,8 @@ tags:
|
|
| 25 |
base_model_relation: quantized
|
| 26 |
---
|
| 27 |
|
|
|
|
|
|
|
| 28 |
# VibeVoice-ASR-BitNet — LiteRT-LM
|
| 29 |
|
| 30 |
[microsoft/VibeVoice-ASR-BitNet](https://huggingface.co/microsoft/VibeVoice-ASR-BitNet) converted to the **LiteRT-LM** (`.litertlm`) format for on-device speech recognition with Google's [LiteRT-LM](https://github.com/google-ai-edge/LiteRT-LM) runtime. **Audio in, text out, in one bundle**: the runtime decodes the clip, runs the bundled audio encoder, and the LLM transcribes — no host-side feature extraction.
|
|
|
|
| 25 |
base_model_relation: quantized
|
| 26 |
---
|
| 27 |
|
| 28 |
+
Measured on device (edge-compat): Galaxy S26 · LiteRT-LM 0.16.1 · GPU · decode 36.1 tok/s · prefill 653 tok/s · TTFT 430 ms · all 1243 ops delegated (2026-09-04); Mac Studio M4 Max · LiteRT-LM 0.16.0 · GPU · decode 138.6 tok/s · prefill 2045 tok/s · TTFT 134 ms (2026-09-04); Galaxy S26 · LiteRT-LM 0.16.1 · CPU · decode 35.4 tok/s · prefill 163 tok/s · TTFT 1.65 s (2026-09-04). Record: https://github.com/john-rocky/edge-compat/blob/main/cards/vibevoice-asr-bitnet/CARD.md
|
| 29 |
+
|
| 30 |
# VibeVoice-ASR-BitNet — LiteRT-LM
|
| 31 |
|
| 32 |
[microsoft/VibeVoice-ASR-BitNet](https://huggingface.co/microsoft/VibeVoice-ASR-BitNet) converted to the **LiteRT-LM** (`.litertlm`) format for on-device speech recognition with Google's [LiteRT-LM](https://github.com/google-ai-edge/LiteRT-LM) runtime. **Audio in, text out, in one bundle**: the runtime decodes the clip, runs the bundled audio encoder, and the LLM transcribes — no host-side feature extraction.
|