Model card: Apache-2.0 license, drop checksum column

README.md

@@ -1,4 +1,5 @@
 ---
+license: apache-2.0
 library_name: pytorch
 pipeline_tag: audio-to-audio
 tags:
@@ -14,9 +15,9 @@ Causal audio-visual target speaker extraction model from the paper: a single-pas
 
 Code, training and evaluation: <https://github.com/JusperLee/Falcon>. Paper: *Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes*.
 
-| File | Config in the code repo | Audio network | Total params | SHA-256 |
-|---|---|---|---|---|
-| `falcon.pt` | `configs/Falcon.yml` | `FalconSpeakerContrastive` | 11.72 M | `a1888b5a3484a38a68c42d1a0e73334b1f2e7924c6e6444b2cfdd27becce928c` |
+| File | Config in the code repo | Audio network | Total params |
+|---|---|---|---|
+| `falcon.pt` | `configs/Falcon.yml` | `FalconSpeakerContrastive` | 11.72 M |
 
 Total parameters include the frozen 11.2 M-parameter FRCNN lip-reading encoder. The file holds only `state_dict` (`audio_model.*`, `video_model.*`), the architecture name and the training epoch; load it with `torch.load(..., weights_only=True)`.
 
@@ -40,3 +41,7 @@ target = model.infer(audio, mouth)                     # (32000,) target speech
 Whole clips: `python infer_file.py --audio mix.wav --mouth mouth.npy --out target.wav`. Live separation in the browser and in Zoom / Tencent Meeting: see `realtime/README.md` in the code repo.
 
 Input: mono 16 kHz audio and synchronized 25 fps grayscale 96×96 mouth crops (center-cropped to 88×88 and normalized inside the runtime).
+
+## License
+
+Apache License 2.0, the same as the code repository.