Merge branch 'main' of http://199.170.132.91:3000/cryptogoth/value-investors-tts into main

voice-training-sets/berkshire-meetings/1994/Dockerfile

@@ -0,0 +1,7 @@
+FROM 12.1.1-cudnn8-runtime-ubuntu22.04
+
+RUN apt update && apt install python3
+RUN pip3 install --upgrade pip
+ADD ./requirements.txt ./requirements.txt
+RUN pip3 install -r requirements.txt
+

voice-training-sets/berkshire-meetings/1994/README.md

@@ -36,4 +36,9 @@ https://stackoverflow.com/questions/9667081/how-do-you-trim-the-audio-files-end-
 
 https://unix.stackexchange.com/questions/381890/play-audio-file-from-a-certain-time-step-in-terminal
 
+## To Train
 
+Move the `wavs` to the output directory along with `config.json`, `metadata.csv`, `train.py` then run
+```
+CUDA_VISIBLE_DEVICES=0 python3 train.py
+```

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

@@ -1 +1 @@
-{"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}]}
+{"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/cryptogoth/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/cryptogoth/src/value-investors-tts/voice-training-sets/berkshire-meetings/1994/models/LJSpeech","phoneme_cache_path":"/home/cryptogoth/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/cryptogoth/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/train.py

@@ -10,6 +10,18 @@ from TTS.tts.models.tacotron2 import Tacotron2
 from TTS.tts.utils.text.tokenizer import TTSTokenizer
 from TTS.utils.audio import AudioProcessor
 
+# https://stackoverflow.com/a/69808279
+# Force CUDNN initialization because it is lazy
+
+import torch
+
+def force_cudnn_initialization():
+    s = 32
+    dev = torch.device('cuda')
+    torch.nn.functional.conv2d(torch.zeros(s, s, s, s, device=dev), torch.zeros(s, s, s, s, device=dev))
+
+force_cudnn_initialization()
+
 # from TTS.tts.datasets.tokenizer import Tokenizer
 
 output_path = "output"