add speed parameter

py/README.md

@@ -4,6 +4,8 @@ This guide provides examples for running TTS inference using `example_onnx.py`.
 
 ## 📰 Update News
 
+**2025.11.19** - Added `--speed` parameter to control speech synthesis speed. Adjust the speed factor to make speech faster or slower while maintaining natural quality.
+
 **2025.11.19** - Added automatic text chunking for long-form inference. Long texts are split into chunks and synthesized with natural pauses.
 
 ## Installation
@@ -85,6 +87,28 @@ This will:
 
 **Note**: When using batch mode (`--batch`), automatic text chunking is disabled. Use non-batch mode for long-form text synthesis.
 
+### Example 5: Adjusting Speech Speed
+Control the speed of speech synthesis:
+```bash
+# Faster speech (speed > 1.0)
+uv run example_onnx.py \
+  --voice-style assets/voice_styles/F2.json \
+  --text "This text will be synthesized at a faster pace." \
+  --speed 1.2
+
+# Slower speech (speed < 1.0)
+uv run example_onnx.py \
+  --voice-style assets/voice_styles/M2.json \
+  --text "This text will be synthesized at a slower, more deliberate pace." \
+  --speed 0.9
+```
+
+This will:
+- Use `--speed 1.2` to generate faster speech
+- Use `--speed 0.9` to generate slower speech
+- Default speed is 1.05 if not specified
+- Recommended speed range is between 0.9 and 1.5 for natural-sounding results
+
 ## Available Arguments
 
 | Argument | Type | Default | Description |
@@ -92,6 +116,7 @@ This will:
 | `--use-gpu` | flag | False | Use GPU for inference (with CPU fallback) |
 | `--onnx-dir` | str | `assets/onnx` | Path to ONNX model directory |
 | `--total-step` | int | 5 | Number of denoising steps (higher = better quality, slower) |
+| `--speed` | float | 1.05 | Speech speed factor (higher = faster, lower = slower) |
 | `--n-test` | int | 4 | Number of times to generate each sample |
 | `--voice-style` | str+ | `assets/voice_styles/M1.json` | Voice style file path(s) |
 | `--text` | str+ | (long default text) | Text(s) to synthesize |

py/example_onnx.py

@@ -26,6 +26,12 @@ def parse_args():
     parser.add_argument(
         "--total-step", type=int, default=5, help="Number of denoising steps"
     )
+    parser.add_argument(
+        "--speed",
+        type=float,
+        default=1.05,
+        help="Speech speed (default: 1.05, higher = faster)",
+    )
     parser.add_argument(
         "--n-test", type=int, default=4, help="Number of times to generate"
     )
@@ -62,6 +68,7 @@ print("=== TTS Inference with ONNX Runtime (Python) ===\n")
 # --- 1. Parse arguments --- #
 args = parse_args()
 total_step = args.total_step
+speed = args.speed
 n_test = args.n_test
 save_dir = args.save_dir
 voice_style_paths = args.voice_style
@@ -84,9 +91,9 @@ for n in range(n_test):
     print(f"\n[{n+1}/{n_test}] Starting synthesis...")
     with timer("Generating speech from text"):
         if batch:
-            wav, duration = text_to_speech.batch(text_list, style, total_step)
+            wav, duration = text_to_speech.batch(text_list, style, total_step, speed)
         else:
-            wav, duration = text_to_speech(text_list[0], style, total_step)
+            wav, duration = text_to_speech(text_list[0], style, total_step, speed)
     if not os.path.exists(save_dir):
         os.makedirs(save_dir)
     for b in range(bsz):

py/helper.py

@@ -86,7 +86,7 @@ class TextToSpeech:
         return noisy_latent, latent_mask
 
     def _infer(
-        self, text_list: list[str], style: Style, total_step: int
+        self, text_list: list[str], style: Style, total_step: int, speed: float = 1.05
     ) -> tuple[np.ndarray, np.ndarray]:
         assert (
             len(text_list) == style.ttl.shape[0]
@@ -96,6 +96,7 @@ class TextToSpeech:
         dur_onnx, *_ = self.dp_ort.run(
             None, {"text_ids": text_ids, "style_dp": style.dp, "text_mask": text_mask}
         )
+        dur_onnx = dur_onnx / speed
         text_emb_onnx, *_ = self.text_enc_ort.run(
             None,
             {"text_ids": text_ids, "style_ttl": style.ttl, "text_mask": text_mask},
@@ -120,7 +121,12 @@ class TextToSpeech:
         return wav, dur_onnx
 
     def __call__(
-        self, text: str, style: Style, total_step: int, silence_duration: float = 0.3
+        self,
+        text: str,
+        style: Style,
+        total_step: int,
+        speed: float = 1.05,
+        silence_duration: float = 0.3,
     ) -> tuple[np.ndarray, np.ndarray]:
         assert (
             style.ttl.shape[0] == 1
@@ -129,7 +135,7 @@ class TextToSpeech:
         wav_cat = None
         dur_cat = None
         for text in text_list:
-            wav, dur_onnx = self._infer([text], style, total_step)
+            wav, dur_onnx = self._infer([text], style, total_step, speed)
             if wav_cat is None:
                 wav_cat = wav
                 dur_cat = dur_onnx
@@ -142,9 +148,9 @@ class TextToSpeech:
         return wav_cat, dur_cat
 
     def batch(
-        self, text_list: list[str], style: Style, total_step: int
+        self, text_list: list[str], style: Style, total_step: int, speed: float = 1.05
     ) -> tuple[np.ndarray, np.ndarray]:
-        return self._infer(text_list, style, total_step)
+        return self._infer(text_list, style, total_step, speed)
 
 
 def length_to_mask(lengths: np.ndarray, max_len: Optional[int] = None) -> np.ndarray: