Add final training configs as well as release 16 KHz model (#19)

* adding final configs for all models

* changs for 16khz

* add latest version for 16khz model

* update package version

---------

Co-authored-by: Ishaan Kumar <[email protected]>

Author: ritheshkumar95

README.md

@@ -32,12 +32,13 @@ pip install git+https://github.com/descriptinc/descript-audio-codec
 
 ### Weights
 Weights are released as part of this repo under MIT license.
-We release weights for models that can natively support 24kHz and 44.1kHz sampling rates.
+We release weights for models that can natively support 16 kHz, 24kHz, and 44.1kHz sampling rates.
 Weights are automatically downloaded when you first run `encode` or `decode` command. You can cache them using one of the following commands
 ```bash
 python3 -m dac download # downloads the default 44kHz variant
 python3 -m dac download --model_type 44khz # downloads the 44kHz variant
 python3 -m dac download --model_type 24khz # downloads the 24kHz variant
+python3 -m dac download --model_type 16khz # downloads the 16kHz variant
 ```
 We provide a Dockerfile that installs all required dependencies for encoding and decoding. The build process caches the default model weights inside the image. This allows the image to be used without an internet connection. [Please refer to instructions below.](#docker-image)
 

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/

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/

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/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.0.4"
+__version__ = "0.0.5"
 
 # preserved here for legacy reasons
 __model_version__ = "latest"