Update README.md
Browse files
README.md
CHANGED
|
@@ -80,6 +80,14 @@ Latency and throughput at concurrency 1, measured over 50 utterances. **TTFP** i
|
|
| 80 |
|
| 81 |
Even on a single concurrent request, Chatterbox-Flash sustains roughly **9× real-time** synthesis at the default setting and **~13× real-time** at `D = 32`, `α = 0.75`, while keeping time-to-first-packet low enough for interactive streaming.
|
| 82 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
# Quality (Seed-TTS test-en)
|
| 84 |
Zero-shot TTS quality on the Seed-TTS English benchmark, under the canonical configuration (`D = 16`). **SIM-o** is speaker similarity to the reference (higher is better), **WER** is word error rate from ASR transcription (lower is better), and **UTMOS** is a predicted naturalness score (higher is better). Results are shown for our two main decoding settings against the Chatterbox backbone and ground-truth audio for reference.
|
| 85 |
|
|
|
|
| 80 |
|
| 81 |
Even on a single concurrent request, Chatterbox-Flash sustains roughly **9× real-time** synthesis at the default setting and **~13× real-time** at `D = 32`, `α = 0.75`, while keeping time-to-first-packet low enough for interactive streaming.
|
| 82 |
|
| 83 |
+
# Apple Silicon (MLX)
|
| 84 |
+
Chatterbox-Flash also runs locally on Apple Silicon via [MLX](https://github.com/ml-explore/mlx). The numbers below were measured on a **Mac M4** at the default configuration; both stay comfortably under real time (`RTF < 1`), and 4-bit quantization gives a further speedup.
|
| 85 |
+
|
| 86 |
+
| Backend | RTF ↓ |
|
| 87 |
+
| --- | :---: |
|
| 88 |
+
| MLX | 0.778 |
|
| 89 |
+
| MLX (4-bit quantized) | **0.665** |
|
| 90 |
+
|
| 91 |
# Quality (Seed-TTS test-en)
|
| 92 |
Zero-shot TTS quality on the Seed-TTS English benchmark, under the canonical configuration (`D = 16`). **SIM-o** is speaker similarity to the reference (higher is better), **WER** is word error rate from ASR transcription (lower is better), and **UTMOS** is a predicted naturalness score (higher is better). Results are shown for our two main decoding settings against the Chatterbox backbone and ground-truth audio for reference.
|
| 93 |
|