Updated noise-cleaned wavs and stats file. Gonna try this on an AWS GPU machine.

voice-training-sets/berkshire-meetings/1994/config.json

@@ -1,173 +1 @@
-{
-    "model": "Berkshire-1994-Warren-Buffett",
-    "run_name": "ljspeech-ddc",
-    "run_description": "tacotron2 with DDC and differential spectral loss.",
-
-    // AUDIO PARAMETERS
-    "audio":{
-        // stft parameters
-        "fft_size": 1024,         // number of stft frequency levels. Size of the linear spectogram frame.
-        "win_length": 1024,      // stft window length in ms.
-        "hop_length": 256,       // stft window hop-lengh in ms.
-        "frame_length_ms": null, // stft window length in ms.If null, 'win_length' is used.
-        "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.
-        "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 (true), TWEB (false), Nancy (true)
-        "trim_db": 60,          // threshold for timming silence. Set this according to your dataset.
-
-        // Griffin-Lim
-        "power": 1.5,           // value to sharpen wav signals after GL algorithm.
-        "griffin_lim_iters": 60,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation.
-
-        // MelSpectrogram parameters
-        "num_mels": 80,         // size of the mel spec frame.
-        "mel_fmin": 50.0,        // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
-        "mel_fmax": 7600.0,     // maximum freq level for mel-spec. Tune for dataset!!
-        "spec_gain": 1,
-
-        // Normalization parameters
-        "signal_norm": true,    // normalize spec values. Mean-Var normalization if 'stats_path' is defined otherwise range normalization defined by the other params.
-        "min_level_db": -100,   // lower bound for normalization
-        "symmetric_norm": true, // move normalization to range [-1, 1]
-        "max_norm": 4.0,        // scale normalization to range [-max_norm, max_norm] or [0, max_norm]
-        "clip_norm": true,      // clip normalized values into the range.
-        "stats_path": "/Users/cryptogoth/Music/value-investors-tts/voice-training-sets/berkshire-meetings/1994/scale_stats.npy"    // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored
-    },
-
-    // VOCABULARY PARAMETERS
-    // if custom character set is not defined,
-    // default set in symbols.py is used
-    // "characters":{
-    //     "pad": "_",
-    //     "eos": "~",
-    //     "bos": "^",
-    //     "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!'(),-.:;? ",
-    //     "punctuations":"!'(),-.:;? ",
-    //     "phonemes":"iyɨʉɯuɪʏʊeøɘəɵɤoɛœɜɞʌɔæɐaɶɑɒᵻʘɓǀɗǃʄǂɠǁʛpbtdʈɖcɟkɡqɢʔɴŋɲɳnɱmʙrʀⱱɾɽɸβfvθðszʃʒʂʐçʝxɣχʁħʕhɦɬɮʋɹɻjɰlɭʎʟˈˌːˑʍwɥʜʢʡɕʑɺɧɚ˞ɫ"
-    // },
-
-    // DISTRIBUTED TRAINING
-    "distributed":{
-        "backend": "nccl",
-        "url": "tcp:\/\/localhost:54321"
-    },
-
-    "reinit_layers": [],    // give a list of layer names to restore from the given checkpoint. If not defined, it reloads all heuristically matching layers.
-
-    // TRAINING
-    "batch_size": 32,       // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
-    "eval_batch_size":16,
-    "r": 7,                 // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled.
-    "gradual_training": [[0, 7, 64], [1, 5, 64], [50000, 3, 32], [130000, 2, 32], [290000, 1, 32]], //set gradual training steps [first_step, r, batch_size]. If it is null, gradual training is disabled. For Tacotron, you might need to reduce the 'batch_size' as you proceeed.
-    "mixed_precision": true,     // level of optimization with NVIDIA's apex feature for automatic mixed FP16/FP32 precision (AMP), NOTE: currently only O1 is supported, and use "O1" to activate.
-
-    // LOSS SETTINGS
-    "loss_masking": true,       // enable / disable loss masking against the sequence padding.
-    "decoder_loss_alpha": 0.5,  // original decoder loss weight. If > 0, it is enabled
-    "postnet_loss_alpha": 0.25, // original postnet loss weight. If > 0, it is enabled
-    "postnet_diff_spec_alpha": 0.25,     // differential spectral loss weight. If > 0, it is enabled
-    "decoder_diff_spec_alpha": 0.25,     // differential spectral loss weight. If > 0, it is enabled
-    "decoder_ssim_alpha": 0.5,     // decoder ssim loss weight. If > 0, it is enabled
-    "postnet_ssim_alpha": 0.25,     // postnet ssim loss weight. If > 0, it is enabled
-    "ga_alpha": 5.0,           // weight for guided attention loss. If > 0, guided attention is enabled.
-    "stopnet_pos_weight": 15.0, // pos class weight for stopnet loss since there are way more negative samples than positive samples.
-
-
-    // VALIDATION
-    "run_eval": true,
-    "test_delay_epochs": 10,  //Until attention is aligned, testing only wastes computation time.
-    "test_sentences_file": null,  // set a file to load sentences to be used for testing. If it is null then we use default english sentences.
-
-    // OPTIMIZER
-    "noam_schedule": false,        // use noam warmup and lr schedule.
-    "grad_clip": 1.0,              // upper limit for gradients for clipping.
-    "epochs": 1000,                // total number of epochs to train.
-    "lr": 0.0001,                  // Initial learning rate. If Noam decay is active, maximum learning rate.
-    "wd": 0.000001,                // Weight decay weight.
-    "warmup_steps": 4000,          // Noam decay steps to increase the learning rate from 0 to "lr"
-    "seq_len_norm": false,         // Normalize eash sample loss with its length to alleviate imbalanced datasets. Use it if your dataset is small or has skewed distribution of sequence lengths.
-
-    // TACOTRON PRENET
-    "memory_size": -1,             // ONLY TACOTRON - size of the memory queue used fro storing last decoder predictions for auto-regression. If < 0, memory queue is disabled and decoder only uses the last prediction frame.
-    "prenet_type": "original",     // "original" or "bn".
-    "prenet_dropout": false,       // enable/disable dropout at prenet.
-
-    // TACOTRON ATTENTION
-    "attention_type": "original",  // 'original' , 'graves', 'dynamic_convolution'
-    "attention_heads": 4,          // number of attention heads (only for 'graves')
-    "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.
-    "transition_agent": false,     // enable/disable transition agent of forward attention.
-    "location_attn": true,         // enable_disable location sensitive attention. It is enabled for TACOTRON by default.
-    "bidirectional_decoder": false,  // use https://arxiv.org/abs/1907.09006. Use it, if attention does not work well with your dataset.
-    "double_decoder_consistency": true,  // use DDC explained here https://erogol.com/solving-attention-problems-of-tts-models-with-double-decoder-consistency-draft/
-    "ddc_r": 7,                           // reduction rate for coarse decoder.
-
-    // STOPNET
-    "stopnet": true,               // Train stopnet predicting the end of synthesis.
-    "separate_stopnet": true,      // Train stopnet seperately if 'stopnet==true'. It prevents stopnet loss to influence the rest of the model. It causes a better model, but it trains SLOWER.
-
-    // TENSORBOARD and LOGGING
-    "print_step": 25,       // Number of steps to log training on console.
-    "tb_plot_step": 100,    // Number of steps to plot TB training figures.
-    "print_eval": false,     // If True, it prints intermediate loss values in evalulation.
-    "save_step": 10000,      // Number of training steps expected to save traninpg stats and checkpoints.
-    "checkpoint": true,     // If true, it saves checkpoints per "save_step"
-    "tb_model_param_stats": false,     // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
-
-    // DATA LOADING
-    "text_cleaner": "phoneme_cleaners",
-    "enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars.
-    "num_loader_workers": 4,        // number of training data loader processes. Don't set it too big. 4-8 are good values.
-    "num_val_loader_workers": 4,    // number of evaluation data loader processes.
-    "batch_group_size": 4,  //Number of batches to shuffle after bucketing.
-    "min_seq_len": 6,       // DATASET-RELATED: minimum text length to use in training
-    "max_seq_len": 153,     // DATASET-RELATED: maximum text length
-    "compute_input_seq_cache": false,  // if true, text sequences are computed before starting training. If phonemes are enabled, they are also computed at this stage.
-    "use_noise_augment": true,
-
-    // PATHS
-    "output_path": "/Users/cryptogoth/Music/value-investors-tts/voice-training-sets/berkshire-meetings/1994/models/LJSpeech/",
-
-    // PHONEMES
-    "phoneme_cache_path": "/Users/cryptogoth/Music/value-investors-tts/voice-training-sets/berkshire-meetings/1994/models/phoneme_cache/",  // phoneme computation is slow, therefore, it caches results in the given folder.
-    "use_phonemes": true,           // use phonemes instead of raw characters. It is suggested for better pronounciation.
-    "phoneme_language": "en-us",     // depending on your target language, pick one from  https://github.com/bootphon/phonemizer#languages
-
-    // MULTI-SPEAKER and GST
-    "use_speaker_embedding": false,      // use speaker embedding to enable multi-speaker learning.
-    "use_gst": false,       			    // use global style tokens
-    "use_external_speaker_embedding_file": false, // if true, forces the model to use external embedding per sample instead of nn.embeddings, that is, it supports external embeddings such as those used at: https://arxiv.org/abs /1806.04558
-    "external_speaker_embedding_file": "../../speakers-vctk-en.json", // if not null and use_external_speaker_embedding_file is true, it is used to load a specific embedding file and thus uses these embeddings instead of nn.embeddings, that is, it supports external embeddings such as those used at: https://arxiv.org/abs /1806.04558
-    "gst":	{			                // gst parameter if gst is enabled
-        "gst_style_input": null,        // Condition the style input either on a
-                                        // -> wave file [path to wave] or
-                                        // -> dictionary using the style tokens {'token1': 'value', 'token2': 'value'} example {"0": 0.15, "1": 0.15, "5": -0.15}
-                                        // with the dictionary being len(dict) <= len(gst_style_tokens).
-        "gst_embedding_dim": 512,
-        "gst_num_heads": 4,
-        "gst_style_tokens": 10,
-        "gst_use_speaker_embedding": false
-	},
-
-    // DATASETS
-    "datasets":   // List of datasets. They all merged and they get different speaker_ids.
-        [
-            {
-                "name": "ljspeech",
-                "path": "/Users/cryptogoth/Music/value-investors-tts/voice-training-sets/berkshire-meetings/1994/",
-                "meta_file_train": "metadata.csv", // for vtck if list, ignore speakers id in list for train, its useful for test cloning with new speakers
-                "meta_file_val": null
-            }
-        ]
-}
-
-
+{"model":"Tacotron2","run_name":"ljspeech-ddc","run_description":"tacotron2 with DDC and differential spectral loss.","audio":{"fft_size":1024,"win_length":1024,"hop_length":256,"frame_length_ms":null,"frame_shift_ms":null,"sample_rate":22050,"preemphasis":0.0,"ref_level_db":20,"do_trim_silence":true,"trim_db":60,"power":1.5,"griffin_lim_iters":60,"num_mels":80,"mel_fmin":50.0,"mel_fmax":7600.0,"spec_gain":1,"signal_norm":true,"min_level_db":-100,"symmetric_norm":true,"max_norm":4.0,"clip_norm":true,"stats_path":"/home/yhs/src/value-investors-tts/voice-training-sets/berkshire-meetings/1994/scale_stats.npy"},"distributed":{"backend":"nccl","url":"tcp://localhost:54321"},"reinit_layers":[],"batch_size":32,"eval_batch_size":16,"r":7,"gradual_training":[[0,7,64],[1,5,64],[50000,3,32],[130000,2,32],[290000,1,32]],"mixed_precision":true,"loss_masking":true,"decoder_loss_alpha":0.5,"postnet_loss_alpha":0.25,"postnet_diff_spec_alpha":0.25,"decoder_diff_spec_alpha":0.25,"decoder_ssim_alpha":0.5,"postnet_ssim_alpha":0.25,"ga_alpha":5.0,"stopnet_pos_weight":15.0,"run_eval":true,"test_delay_epochs":10,"test_sentences_file":null,"noam_schedule":false,"grad_clip":1.0,"epochs":1000,"lr":0.0001,"wd":0.000001,"warmup_steps":4000,"seq_len_norm":false,"memory_size":-1,"prenet_type":"original","prenet_dropout":false,"attention_type":"original","attention_heads":4,"attention_norm":"sigmoid","windowing":false,"use_forward_attn":false,"forward_attn_mask":false,"transition_agent":false,"location_attn":true,"bidirectional_decoder":false,"double_decoder_consistency":true,"ddc_r":7,"stopnet":true,"separate_stopnet":true,"print_step":25,"tb_plot_step":100,"print_eval":false,"save_step":10000,"checkpoint":true,"tb_model_param_stats":false,"text_cleaner":"phoneme_cleaners","enable_eos_bos_chars":false,"num_loader_workers":4,"num_val_loader_workers":4,"batch_group_size":4,"min_seq_len":6,"max_seq_len":153,"compute_input_seq_cache":false,"use_noise_augment":true,"output_path":"/home/yhs/src/value-investors-tts/voice-training-sets/berkshire-meetings/1994/models/LJSpeech","phoneme_cache_path":"/home/yhs/src/value-investors-tts/voice-training-sets/berkshire-meetings/1994/models/phoneme_cache","use_phonemes":true,"phoneme_language":"en-us","use_speaker_embedding":false,"use_gst":false,"use_external_speaker_embedding_file":false,"external_speaker_embedding_file":"../../speakers-vctk-en.json","gst":{"gst_style_input":null,"gst_embedding_dim":512,"gst_num_heads":4,"gst_style_tokens":10,"gst_use_speaker_embedding":false},"datasets":[{"dataset_name":"ljspeech","formatter":"ljspeech","name":"ljspeech","path":"/home/yhs/src/value-investors-tts/voice-training-sets/berkshire-meetings/1994","meta_file_train":"metadata.csv","meta_file_val":null}]}

voice-training-sets/berkshire-meetings/1994/example-config.json

@@ -0,0 +1,175 @@
+{
+    "model": "Tacotron2",
+    "run_name": "ljspeech-ddc",
+    "run_description": "tacotron2 with DDC and differential spectral loss.",
+
+    // AUDIO PARAMETERS
+    "audio":{
+        // stft parameters
+        "fft_size": 1024,         // number of stft frequency levels. Size of the linear spectogram frame.
+        "win_length": 1024,      // stft window length in ms.
+        "hop_length": 256,       // stft window hop-lengh in ms.
+        "frame_length_ms": null, // stft window length in ms.If null, 'win_length' is used.
+        "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.
+        "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 (true), TWEB (false), Nancy (true)
+        "trim_db": 60,          // threshold for timming silence. Set this according to your dataset.
+
+        // Griffin-Lim
+        "power": 1.5,           // value to sharpen wav signals after GL algorithm.
+        "griffin_lim_iters": 60,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation.
+
+        // MelSpectrogram parameters
+        "num_mels": 80,         // size of the mel spec frame.
+        "mel_fmin": 50.0,        // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
+        "mel_fmax": 7600.0,     // maximum freq level for mel-spec. Tune for dataset!!
+        "spec_gain": 1,
+
+        // Normalization parameters
+        "signal_norm": true,    // normalize spec values. Mean-Var normalization if 'stats_path' is defined otherwise range normalization defined by the other params.
+        "min_level_db": -100,   // lower bound for normalization
+        "symmetric_norm": true, // move normalization to range [-1, 1]
+        "max_norm": 4.0,        // scale normalization to range [-max_norm, max_norm] or [0, max_norm]
+        "clip_norm": true,      // clip normalized values into the range.
+        "stats_path": "/Users/cryptogoth/Music/value-investors-tts/voice-training-sets/berkshire-meetings/1994/scale_stats.npy"    // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored
+    },
+
+    // VOCABULARY PARAMETERS
+    // if custom character set is not defined,
+    // default set in symbols.py is used
+    // "characters":{
+    //     "pad": "_",
+    //     "eos": "~",
+    //     "bos": "^",
+    //     "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!'(),-.:;? ",
+    //     "punctuations":"!'(),-.:;? ",
+    //     "phonemes":"iyɨʉɯuɪʏʊeøɘəɵɤoɛœɜɞʌɔæɐaɶɑɒᵻʘɓǀɗǃʄǂɠǁʛpbtdʈɖcɟkɡqɢʔɴŋɲɳnɱmʙrʀⱱɾɽɸβfvθðszʃʒʂʐçʝxɣχʁħʕhɦɬɮʋɹɻjɰlɭʎʟˈˌːˑʍwɥʜʢʡɕʑɺɧɚ˞ɫ"
+    // },
+
+    // DISTRIBUTED TRAINING
+    "distributed":{
+        "backend": "nccl",
+        "url": "tcp:\/\/localhost:54321"
+    },
+
+    "reinit_layers": [],    // give a list of layer names to restore from the given checkpoint. If not defined, it reloads all heuristically matching layers.
+
+    // TRAINING
+    "batch_size": 32,       // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
+    "eval_batch_size":16,
+    "r": 7,                 // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled.
+    "gradual_training": [[0, 7, 64], [1, 5, 64], [50000, 3, 32], [130000, 2, 32], [290000, 1, 32]], //set gradual training steps [first_step, r, batch_size]. If it is null, gradual training is disabled. For Tacotron, you might need to reduce the 'batch_size' as you proceeed.
+    "mixed_precision": true,     // level of optimization with NVIDIA's apex feature for automatic mixed FP16/FP32 precision (AMP), NOTE: currently only O1 is supported, and use "O1" to activate.
+
+    // LOSS SETTINGS
+    "loss_masking": true,       // enable / disable loss masking against the sequence padding.
+    "decoder_loss_alpha": 0.5,  // original decoder loss weight. If > 0, it is enabled
+    "postnet_loss_alpha": 0.25, // original postnet loss weight. If > 0, it is enabled
+    "postnet_diff_spec_alpha": 0.25,     // differential spectral loss weight. If > 0, it is enabled
+    "decoder_diff_spec_alpha": 0.25,     // differential spectral loss weight. If > 0, it is enabled
+    "decoder_ssim_alpha": 0.5,     // decoder ssim loss weight. If > 0, it is enabled
+    "postnet_ssim_alpha": 0.25,     // postnet ssim loss weight. If > 0, it is enabled
+    "ga_alpha": 5.0,           // weight for guided attention loss. If > 0, guided attention is enabled.
+    "stopnet_pos_weight": 15.0, // pos class weight for stopnet loss since there are way more negative samples than positive samples.
+
+
+    // VALIDATION
+    "run_eval": true,
+    "test_delay_epochs": 10,  //Until attention is aligned, testing only wastes computation time.
+    "test_sentences_file": null,  // set a file to load sentences to be used for testing. If it is null then we use default english sentences.
+
+    // OPTIMIZER
+    "noam_schedule": false,        // use noam warmup and lr schedule.
+    "grad_clip": 1.0,              // upper limit for gradients for clipping.
+    "epochs": 1000,                // total number of epochs to train.
+    "lr": 0.0001,                  // Initial learning rate. If Noam decay is active, maximum learning rate.
+    "wd": 0.000001,                // Weight decay weight.
+    "warmup_steps": 4000,          // Noam decay steps to increase the learning rate from 0 to "lr"
+    "seq_len_norm": false,         // Normalize eash sample loss with its length to alleviate imbalanced datasets. Use it if your dataset is small or has skewed distribution of sequence lengths.
+
+    // TACOTRON PRENET
+    "memory_size": -1,             // ONLY TACOTRON - size of the memory queue used fro storing last decoder predictions for auto-regression. If < 0, memory queue is disabled and decoder only uses the last prediction frame.
+    "prenet_type": "original",     // "original" or "bn".
+    "prenet_dropout": false,       // enable/disable dropout at prenet.
+
+    // TACOTRON ATTENTION
+    "attention_type": "original",  // 'original' , 'graves', 'dynamic_convolution'
+    "attention_heads": 4,          // number of attention heads (only for 'graves')
+    "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.
+    "transition_agent": false,     // enable/disable transition agent of forward attention.
+    "location_attn": true,         // enable_disable location sensitive attention. It is enabled for TACOTRON by default.
+    "bidirectional_decoder": false,  // use https://arxiv.org/abs/1907.09006. Use it, if attention does not work well with your dataset.
+    "double_decoder_consistency": true,  // use DDC explained here https://erogol.com/solving-attention-problems-of-tts-models-with-double-decoder-consistency-draft/
+    "ddc_r": 7,                           // reduction rate for coarse decoder.
+
+    // STOPNET
+    "stopnet": true,               // Train stopnet predicting the end of synthesis.
+    "separate_stopnet": true,      // Train stopnet seperately if 'stopnet==true'. It prevents stopnet loss to influence the rest of the model. It causes a better model, but it trains SLOWER.
+
+    // TENSORBOARD and LOGGING
+    "print_step": 25,       // Number of steps to log training on console.
+    "tb_plot_step": 100,    // Number of steps to plot TB training figures.
+    "print_eval": false,     // If True, it prints intermediate loss values in evalulation.
+    "save_step": 10000,      // Number of training steps expected to save traninpg stats and checkpoints.
+    "checkpoint": true,     // If true, it saves checkpoints per "save_step"
+    "tb_model_param_stats": false,     // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
+
+    // DATA LOADING
+    "text_cleaner": "phoneme_cleaners",
+    "enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars.
+    "num_loader_workers": 4,        // number of training data loader processes. Don't set it too big. 4-8 are good values.
+    "num_val_loader_workers": 4,    // number of evaluation data loader processes.
+    "batch_group_size": 4,  //Number of batches to shuffle after bucketing.
+    "min_seq_len": 6,       // DATASET-RELATED: minimum text length to use in training
+    "max_seq_len": 153,     // DATASET-RELATED: maximum text length
+    "compute_input_seq_cache": false,  // if true, text sequences are computed before starting training. If phonemes are enabled, they are also computed at this stage.
+    "use_noise_augment": true,
+
+    // PATHS
+    "output_path": "/Users/cryptogoth/Music/value-investors-tts/voice-training-sets/berkshire-meetings/1994/models/LJSpeech/",
+
+    // PHONEMES
+    "phoneme_cache_path": "/Users/cryptogoth/Music/value-investors-tts/voice-training-sets/berkshire-meetings/1994/models/phoneme_cache/",  // phoneme computation is slow, therefore, it caches results in the given folder.
+    "use_phonemes": true,           // use phonemes instead of raw characters. It is suggested for better pronounciation.
+    "phoneme_language": "en-us",     // depending on your target language, pick one from  https://github.com/bootphon/phonemizer#languages
+
+    // MULTI-SPEAKER and GST
+    "use_speaker_embedding": false,      // use speaker embedding to enable multi-speaker learning.
+    "use_gst": false,       			    // use global style tokens
+    "use_external_speaker_embedding_file": false, // if true, forces the model to use external embedding per sample instead of nn.embeddings, that is, it supports external embeddings such as those used at: https://arxiv.org/abs /1806.04558
+    "external_speaker_embedding_file": "../../speakers-vctk-en.json", // if not null and use_external_speaker_embedding_file is true, it is used to load a specific embedding file and thus uses these embeddings instead of nn.embeddings, that is, it supports external embeddings such as those used at: https://arxiv.org/abs /1806.04558
+    "gst":	{			                // gst parameter if gst is enabled
+        "gst_style_input": null,        // Condition the style input either on a
+                                        // -> wave file [path to wave] or
+                                        // -> dictionary using the style tokens {'token1': 'value', 'token2': 'value'} example {"0": 0.15, "1": 0.15, "5": -0.15}
+                                        // with the dictionary being len(dict) <= len(gst_style_tokens).
+        "gst_embedding_dim": 512,
+        "gst_num_heads": 4,
+        "gst_style_tokens": 10,
+        "gst_use_speaker_embedding": false
+	},
+
+    // DATASETS
+    "datasets":   // List of datasets. They all merged and they get different speaker_ids.
+        [
+            {
+                "dataset_name": "ljspeech",
+                "formatter": "ljspeech",
+                "name": "ljspeech",
+                "path": "/Users/cryptogoth/Music/value-investors-tts/voice-training-sets/berkshire-meetings/1994/",
+                "meta_file_train": "metadata.csv", // for vtck if list, ignore speakers id in list for train, its useful for test cloning with new speakers
+                "meta_file_val": null
+            }
+        ]
+}
+
+

voice-training-sets/berkshire-meetings/1994/modify_config.py

@@ -0,0 +1,23 @@
+import pyjson5
+import os
+
+CUR_DIR = os.getcwd()
+
+with open("./example-config.json") as input_f:
+    with open("./config.json", "w") as output_f:
+        lines = input_f.readlines()
+        data = ''.join(lines)
+        obj = pyjson5.loads(data)
+
+        audio = obj["audio"]
+        audio["stats_path"] = os.path.join(CUR_DIR, 'scale_stats.npy' )
+
+        #output_path = obj['output_path']
+        obj["output_path"] = os.path.join(CUR_DIR, 'models', 'LJSpeech')
+
+        #phoneme_path = obj['phoneme_cache_path']
+        obj["phoneme_cache_path"] = os.path.join(CUR_DIR, 'models', 'phoneme_cache')
+
+        obj["datasets"][0]["path"] = os.path.join(CUR_DIR)
+
+        output_f.write(pyjson5.dumps(obj))

voice-training-sets/berkshire-meetings/1994/modify_metadata.py

@@ -0,0 +1,16 @@
+import os
+
+CUR_DIR = os.getcwd()
+
+with open("./example-metadata.csv") as input_f:
+    with open("./metadata.csv", "w") as output_f:
+        lines = input_f.readlines()
+        write_lines = []
+
+        for line in lines:
+            cols = line.split('|')
+            cols[1] = cols[1].strip()
+            cols.append(cols[1]) # repeat col[1] to be col[2] for the ljspeech format
+            write_lines.append('|'.join(cols))
+
+        output_f.write('\n'.join(write_lines))

voice-training-sets/berkshire-meetings/1994/noise_cleanup.py

@@ -14,7 +14,7 @@ rnn = f"{homedir}/src/rnnoise/examples/rnnoise_demo"
 paths = Path(src).glob("**/*.wav")
 
 for filepath in paths:
-    target_filepath=Path(str(filepath).replace("original", "converted"))
+    target_filepath=Path(str(filepath).replace("original", "wavs"))
     target_dir=os.path.dirname(target_filepath)
 
     if (str(filepath) == str(target_filepath)):
@@ -36,12 +36,16 @@ for filepath in paths:
 
     data, rate = sf.read(target_filepath)
 
-    # peak normalize audio to -1 dB
-    peak_normalized_audio = pyln.normalize.peak(data, -1.0)
-
-    # measure the loudness first
-    meter = pyln.Meter(rate) # create BS.1770 meter
     try:
+        # TODO I don't fully understand why peak loudness could cause an error
+        # but perhaps really loud clips are too distorted to be useful
+        # We might need to catch this and handle it separately than just skipping, like
+        # clips that are too small
+        # peak normalize audio to -1 dB
+        peak_normalized_audio = pyln.normalize.peak(data, -1.0)
+
+        # measure the loudness first
+        meter = pyln.Meter(rate) # create BS.1770 meter
         loudness = meter.integrated_loudness(data)
 
         # loudness normalize audio to -25 dB LUFS

voice-training-sets/berkshire-meetings/1994/requirements.txt

@@ -0,0 +1,3 @@
+TTS
+pyjson5
+pyloudnorm

voice-training-sets/berkshire-meetings/1994/train.py

@@ -0,0 +1,106 @@
+import os
+
+from trainer import Trainer, TrainerArgs
+
+from TTS.config.shared_configs import BaseAudioConfig
+from TTS.tts.configs.shared_configs import BaseDatasetConfig
+from TTS.tts.configs.tacotron2_config import Tacotron2Config
+from TTS.tts.datasets import load_tts_samples
+from TTS.tts.models.tacotron2 import Tacotron2
+from TTS.tts.utils.text.tokenizer import TTSTokenizer
+from TTS.utils.audio import AudioProcessor
+
+# from TTS.tts.datasets.tokenizer import Tokenizer
+
+output_path = "."
+
+# init configs
+dataset_config = BaseDatasetConfig(
+        formatter="ljspeech",
+        dataset_name="ljspeech", meta_file_train="metadata.csv",
+    path=output_path # os.path.join(output_path, "/content/LJSpeech-1.1")
+)
+
+print(str(dataset_config))
+
+audio_config = BaseAudioConfig(
+    sample_rate=22050,
+    do_trim_silence=True,
+    trim_db=60.0,
+    signal_norm=False,
+    mel_fmin=0.0,
+    mel_fmax=8000,
+    spec_gain=1.0,
+    log_func="np.log",
+    ref_level_db=20,
+    preemphasis=0.0,
+)
+
+config = Tacotron2Config(  # This is the config that is saved for the future use
+    audio=audio_config,
+    batch_size=64,
+    eval_batch_size=16,
+    num_loader_workers=4,
+    num_eval_loader_workers=4,
+    run_eval=True,
+    test_delay_epochs=-1,
+    ga_alpha=0.0,
+    decoder_loss_alpha=0.25,
+    postnet_loss_alpha=0.25,
+    postnet_diff_spec_alpha=0,
+    decoder_diff_spec_alpha=0,
+    decoder_ssim_alpha=0,
+    postnet_ssim_alpha=0,
+    r=2,
+    attention_type="dynamic_convolution",
+    double_decoder_consistency=False,
+    epochs=1000,
+    text_cleaner="phoneme_cleaners",
+    use_phonemes=True,
+    phoneme_language="en-us",
+    phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
+    print_step=25,
+    print_eval=True,
+    mixed_precision=False,
+    output_path=output_path,
+    datasets=[dataset_config],
+)
+
+# INITIALIZE THE AUDIO PROCESSOR
+# Audio processor is used for feature extraction and audio I/O.
+# It mainly serves to the dataloader and the training loggers.
+ap = AudioProcessor.init_from_config(config)
+
+# INITIALIZE THE TOKENIZER
+# Tokenizer is used to convert text to sequences of token IDs.
+# If characters are not defined in the config, default characters are passed to the config
+tokenizer, config = TTSTokenizer.init_from_config(config)
+
+# LOAD DATA SAMPLES
+# Each sample is a list of ```[text, audio_file_path, speaker_name]```
+# You can define your custom sample loader returning the list of samples.
+# Or define your custom formatter and pass it to the `load_tts_samples`.
+# Check `TTS.tts.datasets.load_tts_samples` for more details.
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
+
+# INITIALIZE THE MODEL
+# Models take a config object and a speaker manager as input
+# Config defines the details of the model like the number of layers, the size of the embedding, etc.
+# Speaker manager is used by multi-speaker models.
+model = Tacotron2(config, ap, tokenizer)
+
+# INITIALIZE THE TRAINER
+# Trainer provides a generic API to train all the 🐸TTS models with all its perks like mixed-precision training,
+# distributed training, etc.
+trainer = Trainer(
+    TrainerArgs(), config, output_path, model=model, train_samples=train_samples, eval_samples=eval_samples
+)
+
+# AND... 3,2,1... 🚀
+trainer.fit()
+