Refresh model card and examples

train_inflect_micro_fastspeech_v3_pitch.py

@@ -881,7 +881,7 @@ def save_checkpoint(path: Path, model: nn.Module, optim, cfg: MicroFastSpeechCon
 def train(args: argparse.Namespace) -> None:
     device = torch.device(args.device)
     rows = load_rows(args.durations_jsonl, args.max_rows)
-    speakers = {voice: idx for idx, voice in enumerate(sorted({str(r.get("voice_id") or "qwen3_mark") for r in rows}))}
+    speakers = {voice: idx for idx, voice in enumerate(sorted({str(r.get("voice_id") or "mark") for r in rows}))}
     max_phone_id = max(max(map(int, r["phone_ids"])) for r in rows)
     max_tone_id = max(max(map(int, r["tone_ids"])) for r in rows)
     max_lang_id = max(max(map(int, r["lang_ids"])) for r in rows)
@@ -901,7 +901,7 @@ def train(args: argparse.Namespace) -> None:
         use_group_duration_planner=args.group_duration_planner,
     )
     for row in rows:
-        row["speaker_id"] = speakers[str(row.get("voice_id") or "qwen3_mark")]
+        row["speaker_id"] = speakers[str(row.get("voice_id") or "mark")]
     random.Random(args.seed).shuffle(rows)
 
     model = MicroFastSpeech(cfg).to(device)
@@ -981,7 +981,7 @@ def train(args: argparse.Namespace) -> None:
         predicted_prosody_delta_loss = torch.zeros((), device=device)
         if args.predicted_prosody_mel_weight > 0.0 or args.predicted_prosody_delta_weight > 0.0:
             # Train the predictor heads against the acoustic result they produce at
-            # inference, while retaining teacher durations so this path remains
+            # inference, while retaining reference durations so this path remains
             # differentiable and isolates prosody exposure bias.
             predicted_conditioning = model(phone, tone, lang, speaker, durations)
             if args.predicted_prosody_mel_weight > 0.0: