Dikaa16
/

transcut-aligner

forced-alignment

Model card Files Files and versions

Dikaa16 commited on 12 days ago

Commit

4b3cd06

·

verified ·

1 Parent(s): 3dbef85

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ base_model: facebook/wav2vec2-base-960h
 # wav2vec2-base-960h, ONNX, 8-bit (word alignment)
 A converted copy of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h)
-(Apache-2.0), used by Transcut Studio to place each word of a transcript precisely in the audio.
 - Exported to ONNX (opset 17). Input `input_values` `[1, samples]`: 16 kHz mono, zero mean and
   unit variance. Output `logits` `[1, frames, 32]`, one frame per 20 ms, the model's 32 symbols.

 # wav2vec2-base-960h, ONNX, 8-bit (word alignment)
 A converted copy of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h)
+(Apache-2.0), used by [Transcut Studio](https://transcutstudio.com) to place each word of a transcript precisely in the audio.
 - Exported to ONNX (opset 17). Input `input_values` `[1, samples]`: 16 kHz mono, zero mean and
   unit variance. Output `logits` `[1, frames, 32]`, one frame per 20 ms, the model's 32 symbols.