add dac codec

dac-codec/conf/1gpu.yml

@@ -0,0 +1,6 @@
+$include:
+  - conf/base.yml
+
+batch_size: 12
+val_batch_size: 12
+num_workers: 4

dac-codec/conf/ablations/baseline.yml

@@ -0,0 +1,3 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml

dac-codec/conf/ablations/diff-mb.yml

@@ -0,0 +1,22 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+Discriminator.sample_rate: 44100
+Discriminator.fft_sizes: [2048, 1024, 512]
+Discriminator.bands:
+  - [0.0, 0.05]
+  - [0.05, 0.1]
+  - [0.1, 0.25]
+  - [0.25, 0.5]
+  - [0.5, 1.0]
+
+
+# re-weight lambdas to make up for
+# lost discriminators vs baseline
+lambdas:
+  mel/loss: 15.0
+  adv/feat_loss: 5.0
+  adv/gen_loss: 1.0
+  vq/commitment_loss: 0.25
+  vq/codebook_loss: 1.0

dac-codec/conf/ablations/equal-mb.yml

@@ -0,0 +1,22 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+Discriminator.sample_rate: 44100
+Discriminator.fft_sizes: [2048, 1024, 512]
+Discriminator.bands:
+  - [0.0, 0.2]
+  - [0.2, 0.4]
+  - [0.4, 0.6]
+  - [0.6, 0.8]
+  - [0.8, 1.0]
+
+
+# re-weight lambdas to make up for
+# lost discriminators vs baseline
+lambdas:
+  mel/loss: 15.0
+  adv/feat_loss: 5.0
+  adv/gen_loss: 1.0
+  vq/commitment_loss: 0.25
+  vq/codebook_loss: 1.0

dac-codec/conf/ablations/no-adv.yml

@@ -0,0 +1,9 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+lambdas:
+  mel/loss: 1.0
+  waveform/loss: 1.0
+  vq/commitment_loss: 0.25
+  vq/codebook_loss: 1.0

dac-codec/conf/ablations/no-data-balance.yml

@@ -0,0 +1,22 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+train/build_dataset.folders:
+  speech:
+    - /data/daps/train
+    - /data/vctk
+    - /data/vocalset
+    - /data/read_speech
+    - /data/french_speech
+    - /data/emotional_speech/
+    - /data/common_voice/
+    - /data/german_speech/
+    - /data/russian_speech/
+    - /data/spanish_speech/
+  music:
+    - /data/musdb/train
+    - /data/jamendo
+  general:
+    - /data/audioset/data/unbalanced_train_segments/
+    - /data/audioset/data/balanced_train_segments/

dac-codec/conf/ablations/no-low-hop.yml

@@ -0,0 +1,18 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+MelSpectrogramLoss.n_mels: [80]
+MelSpectrogramLoss.window_lengths: [512]
+MelSpectrogramLoss.mel_fmin: [0]
+MelSpectrogramLoss.mel_fmax: [null]
+MelSpectrogramLoss.pow: 1.0
+MelSpectrogramLoss.clamp_eps: 1.0e-5
+MelSpectrogramLoss.mag_weight: 0.0
+
+lambdas:
+  mel/loss: 100.0
+  adv/feat_loss: 2.0
+  adv/gen_loss: 1.0
+  vq/commitment_loss: 0.25
+  vq/codebook_loss: 1.0

dac-codec/conf/ablations/no-mb.yml

@@ -0,0 +1,17 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+Discriminator.sample_rate: 44100
+Discriminator.fft_sizes: [2048, 1024, 512]
+Discriminator.bands:
+  - [0.0, 1.0]
+
+# re-weight lambdas to make up for
+# lost discriminators vs baseline
+lambdas:
+  mel/loss: 15.0
+  adv/feat_loss: 5.0
+  adv/gen_loss: 1.0
+  vq/commitment_loss: 0.25
+  vq/codebook_loss: 1.0

dac-codec/conf/ablations/no-mpd-msd.yml

@@ -0,0 +1,21 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+Discriminator.sample_rate: 44100
+Discriminator.rates: []
+Discriminator.periods: []
+Discriminator.fft_sizes: [2048, 1024, 512]
+Discriminator.bands:
+  - [0.0, 0.1]
+  - [0.1, 0.25]
+  - [0.25, 0.5]
+  - [0.5, 0.75]
+  - [0.75, 1.0]
+
+lambdas:
+  mel/loss: 15.0
+  adv/feat_loss: 2.66
+  adv/gen_loss: 1.0
+  vq/commitment_loss: 0.25
+  vq/codebook_loss: 1.0

dac-codec/conf/ablations/no-mpd.yml

@@ -0,0 +1,21 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+Discriminator.sample_rate: 44100
+Discriminator.rates: [1]
+Discriminator.periods: []
+Discriminator.fft_sizes: [2048, 1024, 512]
+Discriminator.bands:
+  - [0.0, 0.1]
+  - [0.1, 0.25]
+  - [0.25, 0.5]
+  - [0.5, 0.75]
+  - [0.75, 1.0]
+
+lambdas:
+  mel/loss: 15.0
+  adv/feat_loss: 2.5
+  adv/gen_loss: 1.0
+  vq/commitment_loss: 0.25
+  vq/codebook_loss: 1.0

dac-codec/conf/ablations/only-speech.yml

@@ -0,0 +1,22 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+train/build_dataset.folders:
+  speech_fb:
+    - /data/daps/train
+  speech_hq:
+    - /data/vctk
+    - /data/vocalset
+    - /data/read_speech
+    - /data/french_speech
+  speech_uq:
+    - /data/emotional_speech/
+    - /data/common_voice/
+    - /data/german_speech/
+    - /data/russian_speech/
+    - /data/spanish_speech/
+
+val/build_dataset.folders:
+  speech_hq:
+    - /data/daps/val

dac-codec/conf/base.yml

@@ -0,0 +1,123 @@
+# Model setup
+DAC.sample_rate: 44100
+DAC.encoder_dim: 64
+DAC.encoder_rates: [2, 4, 8, 8]
+DAC.decoder_dim: 1536
+DAC.decoder_rates: [8, 8, 4, 2]
+
+# Quantization
+DAC.n_codebooks: 9
+DAC.codebook_size: 1024
+DAC.codebook_dim: 8
+DAC.quantizer_dropout: 1.0
+
+# Discriminator
+Discriminator.sample_rate: 44100
+Discriminator.rates: []
+Discriminator.periods: [2, 3, 5, 7, 11]
+Discriminator.fft_sizes: [2048, 1024, 512]
+Discriminator.bands:
+  - [0.0, 0.1]
+  - [0.1, 0.25]
+  - [0.25, 0.5]
+  - [0.5, 0.75]
+  - [0.75, 1.0]
+
+# Optimization
+AdamW.betas: [0.8, 0.99]
+AdamW.lr: 0.0001
+ExponentialLR.gamma: 0.999996
+
+amp: false
+val_batch_size: 100
+device: cuda
+num_iters: 250000
+save_iters: [10000, 50000, 100000, 200000]
+valid_freq: 1000
+sample_freq: 10000
+num_workers: 32
+val_idx: [0, 1, 2, 3, 4, 5, 6, 7]
+seed: 0
+lambdas:
+  mel/loss: 15.0
+  adv/feat_loss: 2.0
+  adv/gen_loss: 1.0
+  vq/commitment_loss: 0.25
+  vq/codebook_loss: 1.0
+
+VolumeNorm.db: [const, -16]
+
+# Transforms
+build_transform.preprocess:
+  - Identity
+build_transform.augment_prob: 0.0
+build_transform.augment:
+  - Identity
+build_transform.postprocess:
+  - VolumeNorm
+  - RescaleAudio
+  - ShiftPhase
+
+# Loss setup
+MultiScaleSTFTLoss.window_lengths: [2048, 512]
+MelSpectrogramLoss.n_mels: [5, 10, 20, 40, 80, 160, 320]
+MelSpectrogramLoss.window_lengths: [32, 64, 128, 256, 512, 1024, 2048]
+MelSpectrogramLoss.mel_fmin: [0, 0, 0, 0, 0, 0, 0]
+MelSpectrogramLoss.mel_fmax: [null, null, null, null, null, null, null]
+MelSpectrogramLoss.pow: 1.0
+MelSpectrogramLoss.clamp_eps: 1.0e-5
+MelSpectrogramLoss.mag_weight: 0.0
+
+# Data
+batch_size: 72
+train/AudioDataset.duration: 0.38
+train/AudioDataset.n_examples: 10000000
+
+val/AudioDataset.duration: 5.0
+val/build_transform.augment_prob: 1.0
+val/AudioDataset.n_examples: 250
+
+test/AudioDataset.duration: 10.0
+test/build_transform.augment_prob: 1.0
+test/AudioDataset.n_examples: 1000
+
+AudioLoader.shuffle: true
+AudioDataset.without_replacement: true
+
+train/build_dataset.folders:
+  speech_fb:
+    - /data/daps/train
+  speech_hq:
+    - /data/vctk
+    - /data/vocalset
+    - /data/read_speech
+    - /data/french_speech
+  speech_uq:
+    - /data/emotional_speech/
+    - /data/common_voice/
+    - /data/german_speech/
+    - /data/russian_speech/
+    - /data/spanish_speech/
+  music_hq:
+    - /data/musdb/train
+  music_uq:
+    - /data/jamendo
+  general:
+    - /data/audioset/data/unbalanced_train_segments/
+    - /data/audioset/data/balanced_train_segments/
+
+val/build_dataset.folders:
+  speech_hq:
+    - /data/daps/val
+  music_hq:
+    - /data/musdb/test
+  general:
+    - /data/audioset/data/eval_segments/
+
+test/build_dataset.folders:
+  speech_hq:
+    - /data/daps/test
+  music_hq:
+    - /data/musdb/test
+  general:
+    - /data/audioset/data/eval_segments/

dac-codec/conf/downsampling/1024x.yml

@@ -0,0 +1,16 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+# Model setup
+DAC.sample_rate: 44100
+DAC.encoder_dim: 64
+DAC.encoder_rates: [2, 8, 8, 8]
+DAC.decoder_dim: 1536
+DAC.decoder_rates: [8, 4, 4, 2, 2, 2]
+
+# Quantization
+DAC.n_codebooks: 19
+DAC.codebook_size: 1024
+DAC.codebook_dim: 8
+DAC.quantizer_dropout: 1.0

dac-codec/conf/downsampling/128x.yml

@@ -0,0 +1,16 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+# Model setup
+DAC.sample_rate: 44100
+DAC.encoder_dim: 64
+DAC.encoder_rates: [2, 4, 4, 4]
+DAC.decoder_dim: 1536
+DAC.decoder_rates: [4, 4, 2, 2, 2, 1]
+
+# Quantization
+DAC.n_codebooks: 2
+DAC.codebook_size: 1024
+DAC.codebook_dim: 8
+DAC.quantizer_dropout: 1.0

dac-codec/conf/downsampling/1536x.yml

@@ -0,0 +1,16 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+# Model setup
+DAC.sample_rate: 44100
+DAC.encoder_dim: 96
+DAC.encoder_rates: [2, 8, 8, 12]
+DAC.decoder_dim: 1536
+DAC.decoder_rates: [12, 4, 4, 2, 2, 2]
+
+# Quantization
+DAC.n_codebooks: 28
+DAC.codebook_size: 1024
+DAC.codebook_dim: 8
+DAC.quantizer_dropout: 1.0

dac-codec/conf/downsampling/768x.yml

@@ -0,0 +1,16 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+# Model setup
+DAC.sample_rate: 44100
+DAC.encoder_dim: 64
+DAC.encoder_rates: [2, 6, 8, 8]
+DAC.decoder_dim: 1536
+DAC.decoder_rates: [6, 4, 4, 2, 2, 2]
+
+# Quantization
+DAC.n_codebooks: 14
+DAC.codebook_size: 1024
+DAC.codebook_dim: 8
+DAC.quantizer_dropout: 1.0

dac-codec/conf/final/16khz.yml

@@ -0,0 +1,123 @@
+# Model setup
+DAC.sample_rate: 16000
+DAC.encoder_dim: 64
+DAC.encoder_rates: [2, 4, 5, 8]
+DAC.decoder_dim: 1536
+DAC.decoder_rates: [8, 5, 4, 2]
+
+# Quantization
+DAC.n_codebooks: 12
+DAC.codebook_size: 1024
+DAC.codebook_dim: 8
+DAC.quantizer_dropout: 0.5
+
+# Discriminator
+Discriminator.sample_rate: 16000
+Discriminator.rates: []
+Discriminator.periods: [2, 3, 5, 7, 11]
+Discriminator.fft_sizes: [2048, 1024, 512]
+Discriminator.bands:
+  - [0.0, 0.1]
+  - [0.1, 0.25]
+  - [0.25, 0.5]
+  - [0.5, 0.75]
+  - [0.75, 1.0]
+
+# Optimization
+AdamW.betas: [0.8, 0.99]
+AdamW.lr: 0.0001
+ExponentialLR.gamma: 0.999996
+
+amp: false
+val_batch_size: 100
+device: cuda
+num_iters: 400000
+save_iters: [10000, 50000, 100000, 200000]
+valid_freq: 1000
+sample_freq: 10000
+num_workers: 32
+val_idx: [0, 1, 2, 3, 4, 5, 6, 7]
+seed: 0
+lambdas:
+  mel/loss: 15.0
+  adv/feat_loss: 2.0
+  adv/gen_loss: 1.0
+  vq/commitment_loss: 0.25
+  vq/codebook_loss: 1.0
+
+VolumeNorm.db: [const, -16]
+
+# Transforms
+build_transform.preprocess:
+  - Identity
+build_transform.augment_prob: 0.0
+build_transform.augment:
+  - Identity
+build_transform.postprocess:
+  - VolumeNorm
+  - RescaleAudio
+  - ShiftPhase
+
+# Loss setup
+MultiScaleSTFTLoss.window_lengths: [2048, 512]
+MelSpectrogramLoss.n_mels: [5, 10, 20, 40, 80, 160, 320]
+MelSpectrogramLoss.window_lengths: [32, 64, 128, 256, 512, 1024, 2048]
+MelSpectrogramLoss.mel_fmin: [0, 0, 0, 0, 0, 0, 0]
+MelSpectrogramLoss.mel_fmax: [null, null, null, null, null, null, null]
+MelSpectrogramLoss.pow: 1.0
+MelSpectrogramLoss.clamp_eps: 1.0e-5
+MelSpectrogramLoss.mag_weight: 0.0
+
+# Data
+batch_size: 72
+train/AudioDataset.duration: 0.38
+train/AudioDataset.n_examples: 10000000
+
+val/AudioDataset.duration: 5.0
+val/build_transform.augment_prob: 1.0
+val/AudioDataset.n_examples: 250
+
+test/AudioDataset.duration: 10.0
+test/build_transform.augment_prob: 1.0
+test/AudioDataset.n_examples: 1000
+
+AudioLoader.shuffle: true
+AudioDataset.without_replacement: true
+
+train/build_dataset.folders:
+  speech_fb:
+    - /data/daps/train
+  speech_hq:
+    - /data/vctk
+    - /data/vocalset
+    - /data/read_speech
+    - /data/french_speech
+  speech_uq:
+    - /data/emotional_speech/
+    - /data/common_voice/
+    - /data/german_speech/
+    - /data/russian_speech/
+    - /data/spanish_speech/
+  music_hq:
+    - /data/musdb/train
+  music_uq:
+    - /data/jamendo
+  general:
+    - /data/audioset/data/unbalanced_train_segments/
+    - /data/audioset/data/balanced_train_segments/
+
+val/build_dataset.folders:
+  speech_hq:
+    - /data/daps/val
+  music_hq:
+    - /data/musdb/test
+  general:
+    - /data/audioset/data/eval_segments/
+
+test/build_dataset.folders:
+  speech_hq:
+    - /data/daps/test
+  music_hq:
+    - /data/musdb/test
+  general:
+    - /data/audioset/data/eval_segments/

dac-codec/conf/final/24khz.yml

@@ -0,0 +1,123 @@
+# Model setup
+DAC.sample_rate: 24000
+DAC.encoder_dim: 64
+DAC.encoder_rates: [2, 4, 5, 8]
+DAC.decoder_dim: 1536
+DAC.decoder_rates: [8, 5, 4, 2]
+
+# Quantization
+DAC.n_codebooks: 32
+DAC.codebook_size: 1024
+DAC.codebook_dim: 8
+DAC.quantizer_dropout: 0.5
+
+# Discriminator
+Discriminator.sample_rate: 24000
+Discriminator.rates: []
+Discriminator.periods: [2, 3, 5, 7, 11]
+Discriminator.fft_sizes: [2048, 1024, 512]
+Discriminator.bands:
+  - [0.0, 0.1]
+  - [0.1, 0.25]
+  - [0.25, 0.5]
+  - [0.5, 0.75]
+  - [0.75, 1.0]
+
+# Optimization
+AdamW.betas: [0.8, 0.99]
+AdamW.lr: 0.0001
+ExponentialLR.gamma: 0.999996
+
+amp: false
+val_batch_size: 100
+device: cuda
+num_iters: 400000
+save_iters: [10000, 50000, 100000, 200000]
+valid_freq: 1000
+sample_freq: 10000
+num_workers: 32
+val_idx: [0, 1, 2, 3, 4, 5, 6, 7]
+seed: 0
+lambdas:
+  mel/loss: 15.0
+  adv/feat_loss: 2.0
+  adv/gen_loss: 1.0
+  vq/commitment_loss: 0.25
+  vq/codebook_loss: 1.0
+
+VolumeNorm.db: [const, -16]
+
+# Transforms
+build_transform.preprocess:
+  - Identity
+build_transform.augment_prob: 0.0
+build_transform.augment:
+  - Identity
+build_transform.postprocess:
+  - VolumeNorm
+  - RescaleAudio
+  - ShiftPhase
+
+# Loss setup
+MultiScaleSTFTLoss.window_lengths: [2048, 512]
+MelSpectrogramLoss.n_mels: [5, 10, 20, 40, 80, 160, 320]
+MelSpectrogramLoss.window_lengths: [32, 64, 128, 256, 512, 1024, 2048]
+MelSpectrogramLoss.mel_fmin: [0, 0, 0, 0, 0, 0, 0]
+MelSpectrogramLoss.mel_fmax: [null, null, null, null, null, null, null]
+MelSpectrogramLoss.pow: 1.0
+MelSpectrogramLoss.clamp_eps: 1.0e-5
+MelSpectrogramLoss.mag_weight: 0.0
+
+# Data
+batch_size: 72
+train/AudioDataset.duration: 0.38
+train/AudioDataset.n_examples: 10000000
+
+val/AudioDataset.duration: 5.0
+val/build_transform.augment_prob: 1.0
+val/AudioDataset.n_examples: 250
+
+test/AudioDataset.duration: 10.0
+test/build_transform.augment_prob: 1.0
+test/AudioDataset.n_examples: 1000
+
+AudioLoader.shuffle: true
+AudioDataset.without_replacement: true
+
+train/build_dataset.folders:
+  speech_fb:
+    - /data/daps/train
+  speech_hq:
+    - /data/vctk
+    - /data/vocalset
+    - /data/read_speech
+    - /data/french_speech
+  speech_uq:
+    - /data/emotional_speech/
+    - /data/common_voice/
+    - /data/german_speech/
+    - /data/russian_speech/
+    - /data/spanish_speech/
+  music_hq:
+    - /data/musdb/train
+  music_uq:
+    - /data/jamendo
+  general:
+    - /data/audioset/data/unbalanced_train_segments/
+    - /data/audioset/data/balanced_train_segments/
+
+val/build_dataset.folders:
+  speech_hq:
+    - /data/daps/val
+  music_hq:
+    - /data/musdb/test
+  general:
+    - /data/audioset/data/eval_segments/
+
+test/build_dataset.folders:
+  speech_hq:
+    - /data/daps/test
+  music_hq:
+    - /data/musdb/test
+  general:
+    - /data/audioset/data/eval_segments/

dac-codec/conf/final/44khz-16kbps.yml

@@ -0,0 +1,124 @@
+# Model setup
+DAC.sample_rate: 44100
+DAC.encoder_dim: 64
+DAC.encoder_rates: [2, 4, 8, 8]
+DAC.latent_dim: 128
+DAC.decoder_dim: 1536
+DAC.decoder_rates: [8, 8, 4, 2]
+
+# Quantization
+DAC.n_codebooks: 18 # Max bitrate of 16kbps
+DAC.codebook_size: 1024
+DAC.codebook_dim: 8
+DAC.quantizer_dropout: 0.5
+
+# Discriminator
+Discriminator.sample_rate: 44100
+Discriminator.rates: []
+Discriminator.periods: [2, 3, 5, 7, 11]
+Discriminator.fft_sizes: [2048, 1024, 512]
+Discriminator.bands:
+  - [0.0, 0.1]
+  - [0.1, 0.25]
+  - [0.25, 0.5]
+  - [0.5, 0.75]
+  - [0.75, 1.0]
+
+# Optimization
+AdamW.betas: [0.8, 0.99]
+AdamW.lr: 0.0001
+ExponentialLR.gamma: 0.999996
+
+amp: false
+val_batch_size: 100
+device: cuda
+num_iters: 400000
+save_iters: [10000, 50000, 100000, 200000]
+valid_freq: 1000
+sample_freq: 10000
+num_workers: 32
+val_idx: [0, 1, 2, 3, 4, 5, 6, 7]
+seed: 0
+lambdas:
+  mel/loss: 15.0
+  adv/feat_loss: 2.0
+  adv/gen_loss: 1.0
+  vq/commitment_loss: 0.25
+  vq/codebook_loss: 1.0
+
+VolumeNorm.db: [const, -16]
+
+# Transforms
+build_transform.preprocess:
+  - Identity
+build_transform.augment_prob: 0.0
+build_transform.augment:
+  - Identity
+build_transform.postprocess:
+  - VolumeNorm
+  - RescaleAudio
+  - ShiftPhase
+
+# Loss setup
+MultiScaleSTFTLoss.window_lengths: [2048, 512]
+MelSpectrogramLoss.n_mels: [5, 10, 20, 40, 80, 160, 320]
+MelSpectrogramLoss.window_lengths: [32, 64, 128, 256, 512, 1024, 2048]
+MelSpectrogramLoss.mel_fmin: [0, 0, 0, 0, 0, 0, 0]
+MelSpectrogramLoss.mel_fmax: [null, null, null, null, null, null, null]
+MelSpectrogramLoss.pow: 1.0
+MelSpectrogramLoss.clamp_eps: 1.0e-5
+MelSpectrogramLoss.mag_weight: 0.0
+
+# Data
+batch_size: 72
+train/AudioDataset.duration: 0.38
+train/AudioDataset.n_examples: 10000000
+
+val/AudioDataset.duration: 5.0
+val/build_transform.augment_prob: 1.0
+val/AudioDataset.n_examples: 250
+
+test/AudioDataset.duration: 10.0
+test/build_transform.augment_prob: 1.0
+test/AudioDataset.n_examples: 1000
+
+AudioLoader.shuffle: true
+AudioDataset.without_replacement: true
+
+train/build_dataset.folders:
+  speech_fb:
+    - /data/daps/train
+  speech_hq:
+    - /data/vctk
+    - /data/vocalset
+    - /data/read_speech
+    - /data/french_speech
+  speech_uq:
+    - /data/emotional_speech/
+    - /data/common_voice/
+    - /data/german_speech/
+    - /data/russian_speech/
+    - /data/spanish_speech/
+  music_hq:
+    - /data/musdb/train
+  music_uq:
+    - /data/jamendo
+  general:
+    - /data/audioset/data/unbalanced_train_segments/
+    - /data/audioset/data/balanced_train_segments/
+
+val/build_dataset.folders:
+  speech_hq:
+    - /data/daps/val
+  music_hq:
+    - /data/musdb/test
+  general:
+    - /data/audioset/data/eval_segments/
+
+test/build_dataset.folders:
+  speech_hq:
+    - /data/daps/test
+  music_hq:
+    - /data/musdb/test
+  general:
+    - /data/audioset/data/eval_segments/

dac-codec/conf/final/44khz.yml

@@ -0,0 +1,123 @@
+# Model setup
+DAC.sample_rate: 44100
+DAC.encoder_dim: 64
+DAC.encoder_rates: [2, 4, 8, 8]
+DAC.decoder_dim: 1536
+DAC.decoder_rates: [8, 8, 4, 2]
+
+# Quantization
+DAC.n_codebooks: 9
+DAC.codebook_size: 1024
+DAC.codebook_dim: 8
+DAC.quantizer_dropout: 0.5
+
+# Discriminator
+Discriminator.sample_rate: 44100
+Discriminator.rates: []
+Discriminator.periods: [2, 3, 5, 7, 11]
+Discriminator.fft_sizes: [2048, 1024, 512]
+Discriminator.bands:
+  - [0.0, 0.1]
+  - [0.1, 0.25]
+  - [0.25, 0.5]
+  - [0.5, 0.75]
+  - [0.75, 1.0]
+
+# Optimization
+AdamW.betas: [0.8, 0.99]
+AdamW.lr: 0.0001
+ExponentialLR.gamma: 0.999996
+
+amp: false
+val_batch_size: 100
+device: cuda
+num_iters: 400000
+save_iters: [10000, 50000, 100000, 200000]
+valid_freq: 1000
+sample_freq: 10000
+num_workers: 32
+val_idx: [0, 1, 2, 3, 4, 5, 6, 7]
+seed: 0
+lambdas:
+  mel/loss: 15.0
+  adv/feat_loss: 2.0
+  adv/gen_loss: 1.0
+  vq/commitment_loss: 0.25
+  vq/codebook_loss: 1.0
+
+VolumeNorm.db: [const, -16]
+
+# Transforms
+build_transform.preprocess:
+  - Identity
+build_transform.augment_prob: 0.0
+build_transform.augment:
+  - Identity
+build_transform.postprocess:
+  - VolumeNorm
+  - RescaleAudio
+  - ShiftPhase
+
+# Loss setup
+MultiScaleSTFTLoss.window_lengths: [2048, 512]
+MelSpectrogramLoss.n_mels: [5, 10, 20, 40, 80, 160, 320]
+MelSpectrogramLoss.window_lengths: [32, 64, 128, 256, 512, 1024, 2048]
+MelSpectrogramLoss.mel_fmin: [0, 0, 0, 0, 0, 0, 0]
+MelSpectrogramLoss.mel_fmax: [null, null, null, null, null, null, null]
+MelSpectrogramLoss.pow: 1.0
+MelSpectrogramLoss.clamp_eps: 1.0e-5
+MelSpectrogramLoss.mag_weight: 0.0
+
+# Data
+batch_size: 72
+train/AudioDataset.duration: 0.38
+train/AudioDataset.n_examples: 10000000
+
+val/AudioDataset.duration: 5.0
+val/build_transform.augment_prob: 1.0
+val/AudioDataset.n_examples: 250
+
+test/AudioDataset.duration: 10.0
+test/build_transform.augment_prob: 1.0
+test/AudioDataset.n_examples: 1000
+
+AudioLoader.shuffle: true
+AudioDataset.without_replacement: true
+
+train/build_dataset.folders:
+  speech_fb:
+    - /data/daps/train
+  speech_hq:
+    - /data/vctk
+    - /data/vocalset
+    - /data/read_speech
+    - /data/french_speech
+  speech_uq:
+    - /data/emotional_speech/
+    - /data/common_voice/
+    - /data/german_speech/
+    - /data/russian_speech/
+    - /data/spanish_speech/
+  music_hq:
+    - /data/musdb/train
+  music_uq:
+    - /data/jamendo
+  general:
+    - /data/audioset/data/unbalanced_train_segments/
+    - /data/audioset/data/balanced_train_segments/
+
+val/build_dataset.folders:
+  speech_hq:
+    - /data/daps/val
+  music_hq:
+    - /data/musdb/test
+  general:
+    - /data/audioset/data/eval_segments/
+
+test/build_dataset.folders:
+  speech_hq:
+    - /data/daps/test
+  music_hq:
+    - /data/musdb/test
+  general:
+    - /data/audioset/data/eval_segments/

dac-codec/conf/quantizer/24kbps.yml

@@ -0,0 +1,5 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+DAC.n_codebooks: 28

dac-codec/conf/quantizer/256d.yml

@@ -0,0 +1,5 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+DAC.codebook_dim: 256

dac-codec/conf/quantizer/2d.yml

@@ -0,0 +1,5 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+DAC.codebook_dim: 2

dac-codec/conf/quantizer/32d.yml

@@ -0,0 +1,5 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+DAC.codebook_dim: 32

dac-codec/conf/quantizer/4d.yml

@@ -0,0 +1,5 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+DAC.codebook_dim: 4

dac-codec/conf/quantizer/512d.yml

@@ -0,0 +1,5 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+DAC.codebook_dim: 512

dac-codec/conf/quantizer/dropout-0.0.yml

@@ -0,0 +1,5 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+DAC.quantizer_dropout: 0.0

dac-codec/conf/quantizer/dropout-0.25.yml

@@ -0,0 +1,5 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+DAC.quantizer_dropout: 0.25

dac-codec/conf/quantizer/dropout-0.5.yml

@@ -0,0 +1,5 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+DAC.quantizer_dropout: 0.5

dac-codec/conf/size/medium.yml

@@ -0,0 +1,5 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+DAC.decoder_dim: 1024

dac-codec/conf/size/small.yml

@@ -0,0 +1,5 @@
+$include:
+  - conf/base.yml
+  - conf/1gpu.yml
+
+DAC.decoder_dim: 512

dac-codec/dac/__init__.py

@@ -0,0 +1,16 @@
+__version__ = "1.0.0"
+
+# preserved here for legacy reasons
+__model_version__ = "latest"
+
+import audiotools
+
+audiotools.ml.BaseModel.INTERN += ["dac.**"]
+audiotools.ml.BaseModel.EXTERN += ["einops"]
+
+
+from . import nn
+from . import model
+from . import utils
+from .model import DAC
+from .model import DACFile

dac-codec/dac/__main__.py

@@ -0,0 +1,36 @@
+import sys
+
+import argbind
+
+from dac.utils import download
+from dac.utils.decode import decode
+from dac.utils.encode import encode
+
+STAGES = ["encode", "decode", "download"]
+
+
+def run(stage: str):
+    """Run stages.
+
+    Parameters
+    ----------
+    stage : str
+        Stage to run
+    """
+    if stage not in STAGES:
+        raise ValueError(f"Unknown command: {stage}. Allowed commands are {STAGES}")
+    stage_fn = globals()[stage]
+
+    if stage == "download":
+        stage_fn()
+        return
+
+    stage_fn()
+
+
+if __name__ == "__main__":
+    group = sys.argv.pop(1)
+    args = argbind.parse_args(group=group)
+
+    with argbind.scope(args):
+        run(group)

dac-codec/dac/compare/encodec.py

@@ -0,0 +1,54 @@
+import torch
+from audiotools import AudioSignal
+from audiotools.ml import BaseModel
+from encodec import EncodecModel
+
+
+class Encodec(BaseModel):
+    def __init__(self, sample_rate: int = 24000, bandwidth: float = 24.0):
+        super().__init__()
+
+        if sample_rate == 24000:
+            self.model = EncodecModel.encodec_model_24khz()
+        else:
+            self.model = EncodecModel.encodec_model_48khz()
+        self.model.set_target_bandwidth(bandwidth)
+        self.sample_rate = 44100
+
+    def forward(
+        self,
+        audio_data: torch.Tensor,
+        sample_rate: int = 44100,
+        n_quantizers: int = None,
+    ):
+        signal = AudioSignal(audio_data, sample_rate)
+        signal.resample(self.model.sample_rate)
+        recons = self.model(signal.audio_data)
+        recons = AudioSignal(recons, self.model.sample_rate)
+        recons.resample(sample_rate)
+        return {"audio": recons.audio_data}
+
+
+if __name__ == "__main__":
+    import numpy as np
+    from functools import partial
+
+    model = Encodec()
+
+    for n, m in model.named_modules():
+        o = m.extra_repr()
+        p = sum([np.prod(p.size()) for p in m.parameters()])
+        fn = lambda o, p: o + f" {p/1e6:<.3f}M params."
+        setattr(m, "extra_repr", partial(fn, o=o, p=p))
+    print(model)
+    print("Total # of params: ", sum([np.prod(p.size()) for p in model.parameters()]))
+
+    length = 88200 * 2
+    x = torch.randn(1, 1, length).to(model.device)
+    x.requires_grad_(True)
+    x.retain_grad()
+
+    # Make a forward pass
+    out = model(x)["audio"]
+
+    print(x.shape, out.shape)

dac-codec/dac/model/__init__.py

@@ -0,0 +1,4 @@
+from .base import CodecMixin
+from .base import DACFile
+from .dac import DAC
+from .discriminator import Discriminator

dac-codec/dac/model/base.py

@@ -0,0 +1,294 @@
+import math
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Union
+
+import numpy as np
+import torch
+import tqdm
+from audiotools import AudioSignal
+from torch import nn
+
+SUPPORTED_VERSIONS = ["1.0.0"]
+
+
+@dataclass
+class DACFile:
+    codes: torch.Tensor
+
+    # Metadata
+    chunk_length: int
+    original_length: int
+    input_db: float
+    channels: int
+    sample_rate: int
+    padding: bool
+    dac_version: str
+
+    def save(self, path):
+        artifacts = {
+            "codes": self.codes.numpy().astype(np.uint16),
+            "metadata": {
+                "input_db": self.input_db.numpy().astype(np.float32),
+                "original_length": self.original_length,
+                "sample_rate": self.sample_rate,
+                "chunk_length": self.chunk_length,
+                "channels": self.channels,
+                "padding": self.padding,
+                "dac_version": SUPPORTED_VERSIONS[-1],
+            },
+        }
+        path = Path(path).with_suffix(".dac")
+        with open(path, "wb") as f:
+            np.save(f, artifacts)
+        return path
+
+    @classmethod
+    def load(cls, path):
+        artifacts = np.load(path, allow_pickle=True)[()]
+        codes = torch.from_numpy(artifacts["codes"].astype(int))
+        if artifacts["metadata"].get("dac_version", None) not in SUPPORTED_VERSIONS:
+            raise RuntimeError(
+                f"Given file {path} can't be loaded with this version of descript-audio-codec."
+            )
+        return cls(codes=codes, **artifacts["metadata"])
+
+
+class CodecMixin:
+    @property
+    def padding(self):
+        if not hasattr(self, "_padding"):
+            self._padding = True
+        return self._padding
+
+    @padding.setter
+    def padding(self, value):
+        assert isinstance(value, bool)
+
+        layers = [
+            l for l in self.modules() if isinstance(l, (nn.Conv1d, nn.ConvTranspose1d))
+        ]
+
+        for layer in layers:
+            if value:
+                if hasattr(layer, "original_padding"):
+                    layer.padding = layer.original_padding
+            else:
+                layer.original_padding = layer.padding
+                layer.padding = tuple(0 for _ in range(len(layer.padding)))
+
+        self._padding = value
+
+    def get_delay(self):
+        # Any number works here, delay is invariant to input length
+        l_out = self.get_output_length(0)
+        L = l_out
+
+        layers = []
+        for layer in self.modules():
+            if isinstance(layer, (nn.Conv1d, nn.ConvTranspose1d)):
+                layers.append(layer)
+
+        for layer in reversed(layers):
+            d = layer.dilation[0]
+            k = layer.kernel_size[0]
+            s = layer.stride[0]
+
+            if isinstance(layer, nn.ConvTranspose1d):
+                L = ((L - d * (k - 1) - 1) / s) + 1
+            elif isinstance(layer, nn.Conv1d):
+                L = (L - 1) * s + d * (k - 1) + 1
+
+            L = math.ceil(L)
+
+        l_in = L
+
+        return (l_in - l_out) // 2
+
+    def get_output_length(self, input_length):
+        L = input_length
+        # Calculate output length
+        for layer in self.modules():
+            if isinstance(layer, (nn.Conv1d, nn.ConvTranspose1d)):
+                d = layer.dilation[0]
+                k = layer.kernel_size[0]
+                s = layer.stride[0]
+
+                if isinstance(layer, nn.Conv1d):
+                    L = ((L - d * (k - 1) - 1) / s) + 1
+                elif isinstance(layer, nn.ConvTranspose1d):
+                    L = (L - 1) * s + d * (k - 1) + 1
+
+                L = math.floor(L)
+        return L
+
+    @torch.no_grad()
+    def compress(
+        self,
+        audio_path_or_signal: Union[str, Path, AudioSignal],
+        win_duration: float = 1.0,
+        verbose: bool = False,
+        normalize_db: float = -16,
+        n_quantizers: int = None,
+    ) -> DACFile:
+        """Processes an audio signal from a file or AudioSignal object into
+        discrete codes. This function processes the signal in short windows,
+        using constant GPU memory.
+
+        Parameters
+        ----------
+        audio_path_or_signal : Union[str, Path, AudioSignal]
+            audio signal to reconstruct
+        win_duration : float, optional
+            window duration in seconds, by default 5.0
+        verbose : bool, optional
+            by default False
+        normalize_db : float, optional
+            normalize db, by default -16
+
+        Returns
+        -------
+        DACFile
+            Object containing compressed codes and metadata
+            required for decompression
+        """
+        audio_signal = audio_path_or_signal
+        if isinstance(audio_signal, (str, Path)):
+            audio_signal = AudioSignal.load_from_file_with_ffmpeg(str(audio_signal))
+
+        self.eval()
+        original_padding = self.padding
+        original_device = audio_signal.device
+
+        audio_signal = audio_signal.clone()
+        original_sr = audio_signal.sample_rate
+
+        resample_fn = audio_signal.resample
+        loudness_fn = audio_signal.loudness
+
+        # If audio is > 10 minutes long, use the ffmpeg versions
+        if audio_signal.signal_duration >= 10 * 60 * 60:
+            resample_fn = audio_signal.ffmpeg_resample
+            loudness_fn = audio_signal.ffmpeg_loudness
+
+        original_length = audio_signal.signal_length
+        resample_fn(self.sample_rate)
+        input_db = loudness_fn()
+
+        if normalize_db is not None:
+            audio_signal.normalize(normalize_db)
+        audio_signal.ensure_max_of_audio()
+
+        nb, nac, nt = audio_signal.audio_data.shape
+        audio_signal.audio_data = audio_signal.audio_data.reshape(nb * nac, 1, nt)
+        win_duration = (
+            audio_signal.signal_duration if win_duration is None else win_duration
+        )
+
+        if audio_signal.signal_duration <= win_duration:
+            # Unchunked compression (used if signal length < win duration)
+            self.padding = True
+            n_samples = nt
+            hop = nt
+        else:
+            # Chunked inference
+            self.padding = False
+            # Zero-pad signal on either side by the delay
+            audio_signal.zero_pad(self.delay, self.delay)
+            n_samples = int(win_duration * self.sample_rate)
+            # Round n_samples to nearest hop length multiple
+            n_samples = int(math.ceil(n_samples / self.hop_length) * self.hop_length)
+            hop = self.get_output_length(n_samples)
+
+        codes = []
+        range_fn = range if not verbose else tqdm.trange
+
+        for i in range_fn(0, nt, hop):
+            x = audio_signal[..., i : i + n_samples]
+            x = x.zero_pad(0, max(0, n_samples - x.shape[-1]))
+
+            audio_data = x.audio_data.to(self.device)
+            audio_data = self.preprocess(audio_data, self.sample_rate)
+            _, c, _, _, _ = self.encode(audio_data, n_quantizers)
+            codes.append(c.to(original_device))
+            chunk_length = c.shape[-1]
+
+        codes = torch.cat(codes, dim=-1)
+
+        dac_file = DACFile(
+            codes=codes,
+            chunk_length=chunk_length,
+            original_length=original_length,
+            input_db=input_db,
+            channels=nac,
+            sample_rate=original_sr,
+            padding=self.padding,
+            dac_version=SUPPORTED_VERSIONS[-1],
+        )
+
+        if n_quantizers is not None:
+            codes = codes[:, :n_quantizers, :]
+
+        self.padding = original_padding
+        return dac_file
+
+    @torch.no_grad()
+    def decompress(
+        self,
+        obj: Union[str, Path, DACFile],
+        verbose: bool = False,
+    ) -> AudioSignal:
+        """Reconstruct audio from a given .dac file
+
+        Parameters
+        ----------
+        obj : Union[str, Path, DACFile]
+            .dac file location or corresponding DACFile object.
+        verbose : bool, optional
+            Prints progress if True, by default False
+
+        Returns
+        -------
+        AudioSignal
+            Object with the reconstructed audio
+        """
+        self.eval()
+        if isinstance(obj, (str, Path)):
+            obj = DACFile.load(obj)
+
+        original_padding = self.padding
+        self.padding = obj.padding
+
+        range_fn = range if not verbose else tqdm.trange
+        codes = obj.codes
+        original_device = codes.device
+        chunk_length = obj.chunk_length
+        recons = []
+
+        for i in range_fn(0, codes.shape[-1], chunk_length):
+            c = codes[..., i : i + chunk_length].to(self.device)
+            z = self.quantizer.from_codes(c)[0]
+            r = self.decode(z)
+            recons.append(r.to(original_device))
+
+        recons = torch.cat(recons, dim=-1)
+        recons = AudioSignal(recons, self.sample_rate)
+
+        resample_fn = recons.resample
+        loudness_fn = recons.loudness
+
+        # If audio is > 10 minutes long, use the ffmpeg versions
+        if recons.signal_duration >= 10 * 60 * 60:
+            resample_fn = recons.ffmpeg_resample
+            loudness_fn = recons.ffmpeg_loudness
+
+        recons.normalize(obj.input_db)
+        resample_fn(obj.sample_rate)
+        recons = recons[..., : obj.original_length]
+        loudness_fn()
+        recons.audio_data = recons.audio_data.reshape(
+            -1, obj.channels, obj.original_length
+        )
+
+        self.padding = original_padding
+        return recons

dac-codec/dac/model/dac.py

@@ -0,0 +1,364 @@
+import math
+from typing import List
+from typing import Union
+
+import numpy as np
+import torch
+from audiotools import AudioSignal
+from audiotools.ml import BaseModel
+from torch import nn
+
+from .base import CodecMixin
+from dac.nn.layers import Snake1d
+from dac.nn.layers import WNConv1d
+from dac.nn.layers import WNConvTranspose1d
+from dac.nn.quantize import ResidualVectorQuantize
+
+
+def init_weights(m):
+    if isinstance(m, nn.Conv1d):
+        nn.init.trunc_normal_(m.weight, std=0.02)
+        nn.init.constant_(m.bias, 0)
+
+
+class ResidualUnit(nn.Module):
+    def __init__(self, dim: int = 16, dilation: int = 1):
+        super().__init__()
+        pad = ((7 - 1) * dilation) // 2
+        self.block = nn.Sequential(
+            Snake1d(dim),
+            WNConv1d(dim, dim, kernel_size=7, dilation=dilation, padding=pad),
+            Snake1d(dim),
+            WNConv1d(dim, dim, kernel_size=1),
+        )
+
+    def forward(self, x):
+        y = self.block(x)
+        pad = (x.shape[-1] - y.shape[-1]) // 2
+        if pad > 0:
+            x = x[..., pad:-pad]
+        return x + y
+
+
+class EncoderBlock(nn.Module):
+    def __init__(self, dim: int = 16, stride: int = 1):
+        super().__init__()
+        self.block = nn.Sequential(
+            ResidualUnit(dim // 2, dilation=1),
+            ResidualUnit(dim // 2, dilation=3),
+            ResidualUnit(dim // 2, dilation=9),
+            Snake1d(dim // 2),
+            WNConv1d(
+                dim // 2,
+                dim,
+                kernel_size=2 * stride,
+                stride=stride,
+                padding=math.ceil(stride / 2),
+            ),
+        )
+
+    def forward(self, x):
+        return self.block(x)
+
+
+class Encoder(nn.Module):
+    def __init__(
+        self,
+        d_model: int = 64,
+        strides: list = [2, 4, 8, 8],
+        d_latent: int = 64,
+    ):
+        super().__init__()
+        # Create first convolution
+        self.block = [WNConv1d(1, d_model, kernel_size=7, padding=3)]
+
+        # Create EncoderBlocks that double channels as they downsample by `stride`
+        for stride in strides:
+            d_model *= 2
+            self.block += [EncoderBlock(d_model, stride=stride)]
+
+        # Create last convolution
+        self.block += [
+            Snake1d(d_model),
+            WNConv1d(d_model, d_latent, kernel_size=3, padding=1),
+        ]
+
+        # Wrap black into nn.Sequential
+        self.block = nn.Sequential(*self.block)
+        self.enc_dim = d_model
+
+    def forward(self, x):
+        return self.block(x)
+
+
+class DecoderBlock(nn.Module):
+    def __init__(self, input_dim: int = 16, output_dim: int = 8, stride: int = 1):
+        super().__init__()
+        self.block = nn.Sequential(
+            Snake1d(input_dim),
+            WNConvTranspose1d(
+                input_dim,
+                output_dim,
+                kernel_size=2 * stride,
+                stride=stride,
+                padding=math.ceil(stride / 2),
+            ),
+            ResidualUnit(output_dim, dilation=1),
+            ResidualUnit(output_dim, dilation=3),
+            ResidualUnit(output_dim, dilation=9),
+        )
+
+    def forward(self, x):
+        return self.block(x)
+
+
+class Decoder(nn.Module):
+    def __init__(
+        self,
+        input_channel,
+        channels,
+        rates,
+        d_out: int = 1,
+    ):
+        super().__init__()
+
+        # Add first conv layer
+        layers = [WNConv1d(input_channel, channels, kernel_size=7, padding=3)]
+
+        # Add upsampling + MRF blocks
+        for i, stride in enumerate(rates):
+            input_dim = channels // 2**i
+            output_dim = channels // 2 ** (i + 1)
+            layers += [DecoderBlock(input_dim, output_dim, stride)]
+
+        # Add final conv layer
+        layers += [
+            Snake1d(output_dim),
+            WNConv1d(output_dim, d_out, kernel_size=7, padding=3),
+            nn.Tanh(),
+        ]
+
+        self.model = nn.Sequential(*layers)
+
+    def forward(self, x):
+        return self.model(x)
+
+
+class DAC(BaseModel, CodecMixin):
+    def __init__(
+        self,
+        encoder_dim: int = 64,
+        encoder_rates: List[int] = [2, 4, 8, 8],
+        latent_dim: int = None,
+        decoder_dim: int = 1536,
+        decoder_rates: List[int] = [8, 8, 4, 2],
+        n_codebooks: int = 9,
+        codebook_size: int = 1024,
+        codebook_dim: Union[int, list] = 8,
+        quantizer_dropout: bool = False,
+        sample_rate: int = 44100,
+    ):
+        super().__init__()
+
+        self.encoder_dim = encoder_dim
+        self.encoder_rates = encoder_rates
+        self.decoder_dim = decoder_dim
+        self.decoder_rates = decoder_rates
+        self.sample_rate = sample_rate
+
+        if latent_dim is None:
+            latent_dim = encoder_dim * (2 ** len(encoder_rates))
+
+        self.latent_dim = latent_dim
+
+        self.hop_length = np.prod(encoder_rates)
+        self.encoder = Encoder(encoder_dim, encoder_rates, latent_dim)
+
+        self.n_codebooks = n_codebooks
+        self.codebook_size = codebook_size
+        self.codebook_dim = codebook_dim
+        self.quantizer = ResidualVectorQuantize(
+            input_dim=latent_dim,
+            n_codebooks=n_codebooks,
+            codebook_size=codebook_size,
+            codebook_dim=codebook_dim,
+            quantizer_dropout=quantizer_dropout,
+        )
+
+        self.decoder = Decoder(
+            latent_dim,
+            decoder_dim,
+            decoder_rates,
+        )
+        self.sample_rate = sample_rate
+        self.apply(init_weights)
+
+        self.delay = self.get_delay()
+
+    def preprocess(self, audio_data, sample_rate):
+        if sample_rate is None:
+            sample_rate = self.sample_rate
+        assert sample_rate == self.sample_rate
+
+        length = audio_data.shape[-1]
+        right_pad = math.ceil(length / self.hop_length) * self.hop_length - length
+        audio_data = nn.functional.pad(audio_data, (0, right_pad))
+
+        return audio_data
+
+    def encode(
+        self,
+        audio_data: torch.Tensor,
+        n_quantizers: int = None,
+    ):
+        """Encode given audio data and return quantized latent codes
+
+        Parameters
+        ----------
+        audio_data : Tensor[B x 1 x T]
+            Audio data to encode
+        n_quantizers : int, optional
+            Number of quantizers to use, by default None
+            If None, all quantizers are used.
+
+        Returns
+        -------
+        dict
+            A dictionary with the following keys:
+            "z" : Tensor[B x D x T]
+                Quantized continuous representation of input
+            "codes" : Tensor[B x N x T]
+                Codebook indices for each codebook
+                (quantized discrete representation of input)
+            "latents" : Tensor[B x N*D x T]
+                Projected latents (continuous representation of input before quantization)
+            "vq/commitment_loss" : Tensor[1]
+                Commitment loss to train encoder to predict vectors closer to codebook
+                entries
+            "vq/codebook_loss" : Tensor[1]
+                Codebook loss to update the codebook
+            "length" : int
+                Number of samples in input audio
+        """
+        z = self.encoder(audio_data)
+        z, codes, latents, commitment_loss, codebook_loss = self.quantizer(
+            z, n_quantizers
+        )
+        return z, codes, latents, commitment_loss, codebook_loss
+
+    def decode(self, z: torch.Tensor):
+        """Decode given latent codes and return audio data
+
+        Parameters
+        ----------
+        z : Tensor[B x D x T]
+            Quantized continuous representation of input
+        length : int, optional
+            Number of samples in output audio, by default None
+
+        Returns
+        -------
+        dict
+            A dictionary with the following keys:
+            "audio" : Tensor[B x 1 x length]
+                Decoded audio data.
+        """
+        return self.decoder(z)
+
+    def forward(
+        self,
+        audio_data: torch.Tensor,
+        sample_rate: int = None,
+        n_quantizers: int = None,
+    ):
+        """Model forward pass
+
+        Parameters
+        ----------
+        audio_data : Tensor[B x 1 x T]
+            Audio data to encode
+        sample_rate : int, optional
+            Sample rate of audio data in Hz, by default None
+            If None, defaults to `self.sample_rate`
+        n_quantizers : int, optional
+            Number of quantizers to use, by default None.
+            If None, all quantizers are used.
+
+        Returns
+        -------
+        dict
+            A dictionary with the following keys:
+            "z" : Tensor[B x D x T]
+                Quantized continuous representation of input
+            "codes" : Tensor[B x N x T]
+                Codebook indices for each codebook
+                (quantized discrete representation of input)
+            "latents" : Tensor[B x N*D x T]
+                Projected latents (continuous representation of input before quantization)
+            "vq/commitment_loss" : Tensor[1]
+                Commitment loss to train encoder to predict vectors closer to codebook
+                entries
+            "vq/codebook_loss" : Tensor[1]
+                Codebook loss to update the codebook
+            "length" : int
+                Number of samples in input audio
+            "audio" : Tensor[B x 1 x length]
+                Decoded audio data.
+        """
+        length = audio_data.shape[-1]
+        audio_data = self.preprocess(audio_data, sample_rate)
+        z, codes, latents, commitment_loss, codebook_loss = self.encode(
+            audio_data, n_quantizers
+        )
+
+        x = self.decode(z)
+        return {
+            "audio": x[..., :length],
+            "z": z,
+            "codes": codes,
+            "latents": latents,
+            "vq/commitment_loss": commitment_loss,
+            "vq/codebook_loss": codebook_loss,
+        }
+
+
+if __name__ == "__main__":
+    import numpy as np
+    from functools import partial
+
+    model = DAC().to("cpu")
+
+    for n, m in model.named_modules():
+        o = m.extra_repr()
+        p = sum([np.prod(p.size()) for p in m.parameters()])
+        fn = lambda o, p: o + f" {p/1e6:<.3f}M params."
+        setattr(m, "extra_repr", partial(fn, o=o, p=p))
+    print(model)
+    print("Total # of params: ", sum([np.prod(p.size()) for p in model.parameters()]))
+
+    length = 88200 * 2
+    x = torch.randn(1, 1, length).to(model.device)
+    x.requires_grad_(True)
+    x.retain_grad()
+
+    # Make a forward pass
+    out = model(x)["audio"]
+    print("Input shape:", x.shape)
+    print("Output shape:", out.shape)
+
+    # Create gradient variable
+    grad = torch.zeros_like(out)
+    grad[:, :, grad.shape[-1] // 2] = 1
+
+    # Make a backward pass
+    out.backward(grad)
+
+    # Check non-zero values
+    gradmap = x.grad.squeeze(0)
+    gradmap = (gradmap != 0).sum(0)  # sum across features
+    rf = (gradmap != 0).sum()
+
+    print(f"Receptive field: {rf.item()}")
+
+    x = AudioSignal(torch.randn(1, 1, 44100 * 60), 44100)
+    model.decompress(model.compress(x, verbose=True), verbose=True)

dac-codec/dac/model/discriminator.py

@@ -0,0 +1,228 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from audiotools import AudioSignal
+from audiotools import ml
+from audiotools import STFTParams
+from einops import rearrange
+from torch.nn.utils import weight_norm
+
+
+def WNConv1d(*args, **kwargs):
+    act = kwargs.pop("act", True)
+    conv = weight_norm(nn.Conv1d(*args, **kwargs))
+    if not act:
+        return conv
+    return nn.Sequential(conv, nn.LeakyReLU(0.1))
+
+
+def WNConv2d(*args, **kwargs):
+    act = kwargs.pop("act", True)
+    conv = weight_norm(nn.Conv2d(*args, **kwargs))
+    if not act:
+        return conv
+    return nn.Sequential(conv, nn.LeakyReLU(0.1))
+
+
+class MPD(nn.Module):
+    def __init__(self, period):
+        super().__init__()
+        self.period = period
+        self.convs = nn.ModuleList(
+            [
+                WNConv2d(1, 32, (5, 1), (3, 1), padding=(2, 0)),
+                WNConv2d(32, 128, (5, 1), (3, 1), padding=(2, 0)),
+                WNConv2d(128, 512, (5, 1), (3, 1), padding=(2, 0)),
+                WNConv2d(512, 1024, (5, 1), (3, 1), padding=(2, 0)),
+                WNConv2d(1024, 1024, (5, 1), 1, padding=(2, 0)),
+            ]
+        )
+        self.conv_post = WNConv2d(
+            1024, 1, kernel_size=(3, 1), padding=(1, 0), act=False
+        )
+
+    def pad_to_period(self, x):
+        t = x.shape[-1]
+        x = F.pad(x, (0, self.period - t % self.period), mode="reflect")
+        return x
+
+    def forward(self, x):
+        fmap = []
+
+        x = self.pad_to_period(x)
+        x = rearrange(x, "b c (l p) -> b c l p", p=self.period)
+
+        for layer in self.convs:
+            x = layer(x)
+            fmap.append(x)
+
+        x = self.conv_post(x)
+        fmap.append(x)
+
+        return fmap
+
+
+class MSD(nn.Module):
+    def __init__(self, rate: int = 1, sample_rate: int = 44100):
+        super().__init__()
+        self.convs = nn.ModuleList(
+            [
+                WNConv1d(1, 16, 15, 1, padding=7),
+                WNConv1d(16, 64, 41, 4, groups=4, padding=20),
+                WNConv1d(64, 256, 41, 4, groups=16, padding=20),
+                WNConv1d(256, 1024, 41, 4, groups=64, padding=20),
+                WNConv1d(1024, 1024, 41, 4, groups=256, padding=20),
+                WNConv1d(1024, 1024, 5, 1, padding=2),
+            ]
+        )
+        self.conv_post = WNConv1d(1024, 1, 3, 1, padding=1, act=False)
+        self.sample_rate = sample_rate
+        self.rate = rate
+
+    def forward(self, x):
+        x = AudioSignal(x, self.sample_rate)
+        x.resample(self.sample_rate // self.rate)
+        x = x.audio_data
+
+        fmap = []
+
+        for l in self.convs:
+            x = l(x)
+            fmap.append(x)
+        x = self.conv_post(x)
+        fmap.append(x)
+
+        return fmap
+
+
+BANDS = [(0.0, 0.1), (0.1, 0.25), (0.25, 0.5), (0.5, 0.75), (0.75, 1.0)]
+
+
+class MRD(nn.Module):
+    def __init__(
+        self,
+        window_length: int,
+        hop_factor: float = 0.25,
+        sample_rate: int = 44100,
+        bands: list = BANDS,
+    ):
+        """Complex multi-band spectrogram discriminator.
+        Parameters
+        ----------
+        window_length : int
+            Window length of STFT.
+        hop_factor : float, optional
+            Hop factor of the STFT, defaults to ``0.25 * window_length``.
+        sample_rate : int, optional
+            Sampling rate of audio in Hz, by default 44100
+        bands : list, optional
+            Bands to run discriminator over.
+        """
+        super().__init__()
+
+        self.window_length = window_length
+        self.hop_factor = hop_factor
+        self.sample_rate = sample_rate
+        self.stft_params = STFTParams(
+            window_length=window_length,
+            hop_length=int(window_length * hop_factor),
+            match_stride=True,
+        )
+
+        n_fft = window_length // 2 + 1
+        bands = [(int(b[0] * n_fft), int(b[1] * n_fft)) for b in bands]
+        self.bands = bands
+
+        ch = 32
+        convs = lambda: nn.ModuleList(
+            [
+                WNConv2d(2, ch, (3, 9), (1, 1), padding=(1, 4)),
+                WNConv2d(ch, ch, (3, 9), (1, 2), padding=(1, 4)),
+                WNConv2d(ch, ch, (3, 9), (1, 2), padding=(1, 4)),
+                WNConv2d(ch, ch, (3, 9), (1, 2), padding=(1, 4)),
+                WNConv2d(ch, ch, (3, 3), (1, 1), padding=(1, 1)),
+            ]
+        )
+        self.band_convs = nn.ModuleList([convs() for _ in range(len(self.bands))])
+        self.conv_post = WNConv2d(ch, 1, (3, 3), (1, 1), padding=(1, 1), act=False)
+
+    def spectrogram(self, x):
+        x = AudioSignal(x, self.sample_rate, stft_params=self.stft_params)
+        x = torch.view_as_real(x.stft())
+        x = rearrange(x, "b 1 f t c -> (b 1) c t f")
+        # Split into bands
+        x_bands = [x[..., b[0] : b[1]] for b in self.bands]
+        return x_bands
+
+    def forward(self, x):
+        x_bands = self.spectrogram(x)
+        fmap = []
+
+        x = []
+        for band, stack in zip(x_bands, self.band_convs):
+            for layer in stack:
+                band = layer(band)
+                fmap.append(band)
+            x.append(band)
+
+        x = torch.cat(x, dim=-1)
+        x = self.conv_post(x)
+        fmap.append(x)
+
+        return fmap
+
+
+class Discriminator(ml.BaseModel):
+    def __init__(
+        self,
+        rates: list = [],
+        periods: list = [2, 3, 5, 7, 11],
+        fft_sizes: list = [2048, 1024, 512],
+        sample_rate: int = 44100,
+        bands: list = BANDS,
+    ):
+        """Discriminator that combines multiple discriminators.
+
+        Parameters
+        ----------
+        rates : list, optional
+            sampling rates (in Hz) to run MSD at, by default []
+            If empty, MSD is not used.
+        periods : list, optional
+            periods (of samples) to run MPD at, by default [2, 3, 5, 7, 11]
+        fft_sizes : list, optional
+            Window sizes of the FFT to run MRD at, by default [2048, 1024, 512]
+        sample_rate : int, optional
+            Sampling rate of audio in Hz, by default 44100
+        bands : list, optional
+            Bands to run MRD at, by default `BANDS`
+        """
+        super().__init__()
+        discs = []
+        discs += [MPD(p) for p in periods]
+        discs += [MSD(r, sample_rate=sample_rate) for r in rates]
+        discs += [MRD(f, sample_rate=sample_rate, bands=bands) for f in fft_sizes]
+        self.discriminators = nn.ModuleList(discs)
+
+    def preprocess(self, y):
+        # Remove DC offset
+        y = y - y.mean(dim=-1, keepdims=True)
+        # Peak normalize the volume of input audio
+        y = 0.8 * y / (y.abs().max(dim=-1, keepdim=True)[0] + 1e-9)
+        return y
+
+    def forward(self, x):
+        x = self.preprocess(x)
+        fmaps = [d(x) for d in self.discriminators]
+        return fmaps
+
+
+if __name__ == "__main__":
+    disc = Discriminator()
+    x = torch.zeros(1, 1, 44100)
+    results = disc(x)
+    for i, result in enumerate(results):
+        print(f"disc{i}")
+        for i, r in enumerate(result):
+            print(r.shape, r.mean(), r.min(), r.max())
+        print()

dac-codec/dac/nn/__init__.py

@@ -0,0 +1,3 @@
+from . import layers
+from . import loss
+from . import quantize