diff --git a/config.json b/config.json index bdeecdea..77a223dc 100644 --- a/config.json +++ b/config.json @@ -13,12 +13,12 @@ "frame_shift_ms": null, // stft window hop-lengh in ms. If null, 'hop_length' is used. // Audio processing parameters - "sample_rate": 22050, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled. + "sample_rate": 22050, // DATASET-RELATED: wav sample-rate. "preemphasis": 0.0, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis. "ref_level_db": 20, // reference level db, theoretically 20db is the sound of air. // Silence trimming - "do_trim_silence": true,// enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true) + "do_trim_silence": true,// enable trimming of slience of audio as you load it. LJspeech (true), TWEB (false), Nancy (true) "trim_db": 60, // threshold for timming silence. Set this according to your dataset. // Griffin-Lim @@ -89,7 +89,7 @@ // ATTENTION "attention_type": "original", // 'original' or 'graves' "attention_heads": 4, // number of attention heads (only for 'graves') - "attention_norm": "sigmoid", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron. + "attention_norm": "sigmoid", // softmax or sigmoid. "windowing": false, // Enables attention windowing. Used only in eval mode. "use_forward_attn": false, // if it uses forward attention. In general, it aligns faster. "forward_attn_mask": false, // Additional masking forcing monotonicity only in eval mode.