showcase: step 70k: 5 listening samples (AudioSeal-watermarked)

README.md

@@ -81,7 +81,7 @@ and seed); the players hold this page's own takes, which can differ slightly.
 
 ### Earlier and later checkpoints (training history)
 
-The other checkpoints of the same training run (11), kept for comparison; they are not the release. The same five texts
+The other checkpoints of the same training run (12), kept for comparison; they are not the release. The same five texts
 and voices, made with the default bandwidth condition. Click one to open it.
 
 <details>
@@ -238,6 +238,20 @@ and voices, made with the default bandwidth condition. Click one to open it.
 
 </details>
 
+<details>
+<summary><b>Step 70k</b>: echo-dev WER 0.67 % · UTMOS 3.69</summary>
+
+<table>
+<tr><th>What the model reads</th><th>Model output, step 70k</th></tr>
+<tr><td><b>Short sentence</b></td><td><audio controls src="https://huggingface.co/VoiceHub/DACFlow-EN-10k/resolve/main/samples/step_0070000/01-short.wav"></audio></td></tr>
+<tr><td><b>Question</b></td><td><audio controls src="https://huggingface.co/VoiceHub/DACFlow-EN-10k/resolve/main/samples/step_0070000/02-question.wav"></audio></td></tr>
+<tr><td><b>Numbers, dates, abbreviations</b></td><td><audio controls src="https://huggingface.co/VoiceHub/DACFlow-EN-10k/resolve/main/samples/step_0070000/03-numbers.wav"></audio></td></tr>
+<tr><td><b>Conversation (~10 s)</b></td><td><audio controls src="https://huggingface.co/VoiceHub/DACFlow-EN-10k/resolve/main/samples/step_0070000/04-conversational.wav"></audio></td></tr>
+<tr><td><b>Long passage (~20 s)</b></td><td><audio controls src="https://huggingface.co/VoiceHub/DACFlow-EN-10k/resolve/main/samples/step_0070000/05-long.wav"></audio></td></tr>
+</table>
+
+</details>
+
 ## Results
 
 ### The model: step 100k
@@ -271,7 +285,7 @@ Every checkpoint of the training run, scored with the default bandwidth conditio
 | **step 100k** (the model) | 0.69 % | 0.787 | 3.85 | 1.54 % | 0.499 | 3.78 | [listen](#listen) | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0100000) |
 | step 90k | 0.74 % | 0.782 | 3.78 | - | - | - | [listen](#listen) | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0090000) |
 | step 80k | 0.78 % | 0.776 | 3.73 | 1.58 % | 0.507 | 3.68 | [listen](#listen) | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0080000) |
-| step 70k | 0.67 % | 0.766 | 3.69 | - | - | - | pending | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0070000) |
+| step 70k | 0.67 % | 0.766 | 3.69 | - | - | - | [listen](#listen) | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0070000) |
 | step 60k | 0.69 % | 0.759 | 3.62 | 1.61 % | 0.537 | 3.56 | pending | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0060000) |
 | step 50k | 0.74 % | 0.754 | 3.56 | - | - | - | pending | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0050000) |
 | step 40k | 0.74 % | 0.748 | 3.50 | 1.85 % | 0.536 | 3.48 | pending | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0040000) |

samples/step_0070000/01-short.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ed39424d3ae6c304f4ea17cd030ea1d14f1d5d6d27054d568eb1f7f91526ac9
+size 491564

samples/step_0070000/02-question.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2423de3a01bf49c2fae25107743f34f1e0748ebcac0cf4d7485536dd1fa56e04
+size 583724

samples/step_0070000/03-numbers.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88f1cd4c87255168d01730933d13675aa15a1ca9002d97316abdc0e822d43861
+size 841004

samples/step_0070000/04-conversational.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6437479879b21c243c6360a6270f7eb662d593315c8ebe79e07ad31190889435
+size 1129004

samples/step_0070000/05-long.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25cbcaf5e77186d73573e2e53d15199306a6ea50ae9fde6f07cacea959f52f6f
+size 1691564

showcase.json

@@ -1,5 +1,5 @@
 {
- "card_sha": "7264a25ef67f1b7d",
+ "card_sha": "349838f6b8ca447b",
  "checkpoints": {
   "en_base/step_0020000": {
    "added": "2026-10-03T02:01:41Z",
@@ -329,6 +329,75 @@
    "provenance": "catalog echo_en_v1 (data-4255c6734a7d5b5e): echo_en",
    "recipe_arm": false,
    "run": "en_base",
+   "samples": {
+    "added": "2026-10-05T01:16:12Z",
+    "code_commit": "029dec6",
+    "folder": "samples/step_0070000",
+    "items_sha": "8fcd29112a5e183c",
+    "rows": [
+     {
+      "file": "samples/step_0070000/01-short.wav",
+      "gen_seconds": 0.92,
+      "item": "01-short",
+      "seconds": 5.12,
+      "watermark": "audioseal_wm_16bits",
+      "watermark_bits": "0100110101010100",
+      "watermark_score": 1.0
+     },
+     {
+      "file": "samples/step_0070000/02-question.wav",
+      "gen_seconds": 0.83,
+      "item": "02-question",
+      "seconds": 6.08,
+      "watermark": "audioseal_wm_16bits",
+      "watermark_bits": "0100110101010100",
+      "watermark_score": 1.0
+     },
+     {
+      "file": "samples/step_0070000/03-numbers.wav",
+      "gen_seconds": 0.87,
+      "item": "03-numbers",
+      "seconds": 8.76,
+      "watermark": "audioseal_wm_16bits",
+      "watermark_bits": "0100110101010100",
+      "watermark_score": 1.0
+     },
+     {
+      "file": "samples/step_0070000/04-conversational.wav",
+      "gen_seconds": 0.87,
+      "item": "04-conversational",
+      "seconds": 11.76,
+      "watermark": "audioseal_wm_16bits",
+      "watermark_bits": "0100110101010100",
+      "watermark_score": 1.0
+     },
+     {
+      "file": "samples/step_0070000/05-long.wav",
+      "gen_seconds": 1.68,
+      "item": "05-long",
+      "seconds": 17.62,
+      "watermark": "audioseal_wm_16bits",
+      "watermark_bits": "0100110101010100",
+      "watermark_score": 1.0
+     }
+    ],
+    "sampler": {
+     "cfg_mode": "joint",
+     "cfg_rescale": 0.0,
+     "cfg_t_max": 1.0,
+     "cfg_t_min": 0.0,
+     "cfg_w": 4.0,
+     "gpu_peak_gb": 4.14,
+     "noise_scale": 0.9,
+     "out_lufs": -16.0,
+     "schedule": "sway",
+     "source": "eval_args.json",
+     "steps": 32,
+     "sway": -1.0,
+     "w_speaker": 3.5,
+     "w_text": 2.5
+    }
+   },
    "source": "en_base/export/model_step_00070000.pt",
    "step": 70000,
    "train_sources": [