Remove purged example audio references; use your_call.wav placeholder

README.md

@@ -37,18 +37,18 @@ just `transformers` + `descript-audio-codec`.
 ```bash
 pip install torch torchaudio "transformers>=4.56" "descript-audio-codec>=1.0.0" soundfile "huggingface_hub[cli]"
 
-# pull the CLI + the two slim checkpoints + example clip straight from the Hub
+# pull the CLI + the two slim checkpoints from the Hub
 hf auth login   # private repo: log in first (or export HF_TOKEN=hf_...)
 hf download Scicom-intl/sidon-callcentre \
     infer_callcentre.py fe_callcentre/fe_adapter_full.pt \
-    decoder_callcentre/decoder_only.pt examples/audio1.mp3 --local-dir sidon-callcentre
+    decoder_callcentre/decoder_only.pt --local-dir sidon-callcentre
 
 cd sidon-callcentre && python infer_callcentre.py \
-    --input examples/audio1.mp3 --out-dir out \
+    --input your_call.wav --out-dir out \
     --fe-adapter fe_callcentre/fe_adapter_full.pt \
     --decoder decoder_callcentre/decoder_only.pt \
     --chunk 0 --device cuda   # --chunk 0 = NO chunking (default single pass); --device cpu if no GPU
-# -> out/audio1_restored48k.wav (clean 48 kHz)  +  out/audio1_orig48k.wav (A/B)
+# -> out/your_call_restored48k.wav (clean 48 kHz)  +  out/your_call_orig48k.wav (A/B)
 ```
 
 Prefer Python (load weights from the Hub with `hf_hub_download`)? See **[Python](#python-pull-weights-from-the-hub)** below.
@@ -66,7 +66,6 @@ Use the **current-run** checkpoints under `fe_callcentre/` and `decoder_callcent
 | `decoder_callcentre/decoder_only.pt` | **decoder (inference)** — 188M DAC decoder | ~0.75 GB |
 | `fe_callcentre/last.pt`, `decoder_callcentre/last.pt` | raw checkpoints (resume training) | ~2.5 / 2.8 GB |
 | `infer_callcentre.py` | inference CLI (below) | — |
-| `examples/audio1.mp3` | example 8 kHz call-centre clip | — |
 
 For inference you only need the two slim files + `infer_callcentre.py`. *(Root-level
 `fe_adapter_full.pt` / `decoder_only.pt` are from an earlier run and are superseded.)*
@@ -76,19 +75,18 @@ For inference you only need the two slim files + `infer_callcentre.py`. *(Root-l
 ```bash
 pip install torch torchaudio "transformers>=4.56" "descript-audio-codec>=1.0.0" soundfile "huggingface_hub[cli]"
 
-# pull the CLI + the two slim checkpoints + the example clip, straight from this repo
+# pull the CLI + the two slim checkpoints, straight from this repo
 hf auth login   # private repo: log in first (or export HF_TOKEN=hf_...)
 hf download Scicom-intl/sidon-callcentre \
     infer_callcentre.py \
     fe_callcentre/fe_adapter_full.pt \
     decoder_callcentre/decoder_only.pt \
-    examples/audio1.mp3 \
     --local-dir sidon-callcentre
 cd sidon-callcentre
 
-# restore the example clip end-to-end
+# restore your audio end-to-end
 python infer_callcentre.py \
-    --input examples/audio1.mp3 \
+    --input your_call.wav \
     --out-dir out \
     --fe-adapter fe_callcentre/fe_adapter_full.pt \
     --decoder   decoder_callcentre/decoder_only.pt \
@@ -96,8 +94,8 @@ python infer_callcentre.py \
 ```
 
 Outputs:
-- `out/audio1_restored48k.wav` — the restored **clean 48 kHz** speech.
-- `out/audio1_orig48k.wav` — the input, naively upsampled to 48 kHz (no model), for an A/B listen.
+- `out/your_call_restored48k.wav` — the restored **clean 48 kHz** speech.
+- `out/your_call_orig48k.wav` — the input, naively upsampled to 48 kHz (no model), for an A/B listen.
 
 `--input` accepts a **file or a directory** (`.wav/.flac/.mp3/.ogg/.opus/.m4a`). Stereo (e.g.
 agent/customer on separate channels) is restored per channel and recombined.
@@ -142,7 +140,7 @@ def restore(path, out="restored48k.wav"):                # single straight pass
     y = dec(fe(**feats).last_hidden_state.transpose(1, 2)).squeeze().float().cpu().numpy()
     sf.write(out, y / (np.abs(y).max() + 1e-9) * 0.97, SR_OUT); print("wrote", out)
 
-restore(hf_hub_download(REPO, "examples/audio1.mp3"))
+restore("your_call.wav")   # <-- your own telephony/call-centre audio
 ```
 
 ## Model details