Closed justghostof closed 4 years ago
just pasting your error messages does not help for a thing
system:Linux version 4.15.0-1075-azure (buildd@lcy01-amd64-018) (gcc version 5.4.0 20160609 (Ubuntu 5.4.0-6ubuntu1~16.04.12))
Python 3.8.2
config.json:
{
"model": "Tacotron2", // one of the model in models/
"run_name": "ljspeech-stft_params",
"run_description": "tacotron2 cosntant stf parameters",
// AUDIO PARAMETERS
"audio":{
// Audio processing parameters
"num_mels": 80, // size of the mel spec frame.
"num_freq": 1025, // number of stft frequency levels. Size of the linear spectogram frame.
"sample_rate": 48000, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
"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.
"preemphasis": 0.98, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
"min_level_db": -100, // normalization range
"ref_level_db": 20, // reference level db, theoretically 20db is the sound of air.
"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.
// Normalization parameters
"signal_norm": true, // normalize the spec values in range [0, 1]
"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.
"mel_fmin": 0.0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
"mel_fmax": 8000.0, // maximum freq level for mel-spec. Tune for dataset!!
"do_trim_silence": true, // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
"trim_db": 60 // threshold for timming silence. Set this according to your dataset.
},
// 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.
"loss_masking": true, // enable / disable loss masking against the sequence padding.
// 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": true, // enable/disable dropout at prenet.
// ATTENTION
"attention_type": "original", // 'original' or 'graves'
"attention_heads": 4, // number of attention heads (only for 'graves')
"attention_norm": "sigmoid", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron.
"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": false, // 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.
// 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 traning on console.
"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": 0, //Number of batches to shuffle after bucketing.
"min_seq_len": 6, // DATASET-RELATED: minimum text length to use in training
"max_seq_len": 150, // DATASET-RELATED: maximum text length
// PATHS
"output_path": "/root/Trainings/",
// PHONEMES
"phoneme_cache_path": "mozilla_us_phonemes_2_1", // 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": "zh", // 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.
"style_wav_for_test": null, // path to style wav file to be used in TacotronGST inference.
"use_gst": false, // TACOTRON ONLY: use global style tokens
// DATASETS
"datasets": // List of datasets. They all merged and they get different speaker_ids.
[
{
"name": "ljspeech",
"path": "/root/TTS/data/allmj/",
"meta_file_train": "metadata.csv",
"meta_file_val": null
}
]
}
metadata.csv
1|重新发一个吧|重新发一个吧
2|重新发一个重新发一个|重新发一个重新发一个
3|管理员不要拿啊|管理员不要拿啊
4|两个红包大家随便抢|两个红包大家随便抢
5|呵呵|呵呵
6|发了啊|发了啊
7|别他妈刷了 谢谢你们啊|别他妈刷了 谢谢你们啊
8|发完了|发完了
9|发完了我现在还不知道唱什么歌|发完了我现在还不知道唱什么歌
10|又炸了|又炸了
11|又唱绝帝 每次都唱绝帝 妈的 操|又唱绝帝 每次都唱绝帝 妈的 操
12|我还没想好唱什么歌|我还没想好唱什么歌
13|不过有一说一我们|不过有一说一我们
14|五月天的翻唱|五月天的翻唱
15|然后是我自己重新编曲的|然后是我自己重新编曲的
16|敬请期待|敬请期待
17|这不算剧透 我们都快做好了都|这不算剧透 我们都快做好了都
18|巨牛逼|巨牛逼
19|找伴奏嘛|找伴奏嘛
20|欸没有伴奏|欸没有伴奏
21|我用一下小启跟 我用一下小启跟 那个 谁 谁 谁 谁 谁写的|我用一下小启跟 我用一下小启跟 那个 谁 谁 谁 谁 谁写的
22|中文版歌词|中文版歌词
23|没办法 日文对咱实在是|没办法 日文对咱实在是
24|看得我又想玩了 诶呦 有点想|看得我又想玩了 诶呦 有点想
25|鸡儿其实特别硬的|鸡儿其实特别硬的
26|两个人在玩动森|两个人在玩动森
27|额 三个人在玩生化|额 三个人在玩生化
28|生化三|生化三
29|然后 他妈的|然后他妈的
30|然后|然后
31|我也不知道该我也不知道该直播什么 这生化三打完跟没打似的我感觉 一点 一点意思都没有|我也不知道该我也不知道该直播什么 这生化三打完跟没打似的我感觉 一点 一点意思都没有
File "train.py", line 352,“for”Code block not executed
I can't reproduce the problem in either dev and master branch
This is my entire TTS directory file
Maybe it's my fault I clone the Repository again and then it is working
I'm sorry to bother you And thankyou very much
I am facing the same issue. I cloned repo again but it did not work. Does number of odd file has to do with anything? @erogol @twerkmeister @reuben @nmstoker
` { "model": "Tacotron2", "run_name": "ljspeech", "run_description": "tacotron2",
// AUDIO PARAMETERS
"audio":{
// stft parameters
"num_freq": 513, // 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. If different than the original data, it is resampled.
"preemphasis": 0.0, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
"ref_level_db": 20, // reference level db, theoretically 20db is the sound of air.
// Silence trimming
"do_trim_silence": true,// enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
"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": 0.0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
"mel_fmax": 8000.0, // maximum freq level for mel-spec. Tune for dataset!!
// 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": null // 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.
"loss_masking": true, // enable / disable loss masking against the sequence padding.
"ga_alpha": 10.0, // weight for guided attention loss. If > 0, guided attention is enabled.
// 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": true, // enable/disable dropout at prenet.
// ATTENTION
"attention_type": "original", // 'original' or 'graves'
"attention_heads": 4, // number of attention heads (only for 'graves')
"attention_norm": "sigmoid", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron.
"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.
// 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 traning on console.
"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": 0, //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
// PATHS
"output_path": "/home/sadam/Projects/Italian_TTS/TTS/Models/LJSpeech/",
// PHONEMES
"phoneme_cache_path": "/home/sadam/Projects/Italian_TTS/TTS/mozilla_us_phonemes_3", // 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": "it", // 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.
"style_wav_for_test": null, // path to style wav file to be used in TacotronGST inference.
"use_gst": false, // TACOTRON ONLY: use global style tokens
// DATASETS
"datasets": // List of datasets. They all merged and they get different speaker_ids.
[
{
"name": "ljspeech",
"path": "/home/sadam/Projects/Italian_TTS/LJSpeech-1.1/",
"meta_file_train": "metadata.csv",
"meta_file_val": null
}
]
}
`
`
Using CUDA: False Number of GPUs: 0 Git Hash: f320992 Experiment folder: /home/sadam/Projects/Italian_TTS/TTS/Models/LJSpeech/ljspeech-June-05-2020_06+53PM-f320992 Setting up Audio Processor... | > sample_rate:22050 | > num_mels:80 | > min_level_db:-100 | > frame_shift_ms:None | > frame_length_ms:None | > ref_level_db:20 | > num_freq:513 | > power:1.5 | > preemphasis:0.0 | > griffin_lim_iters:60 | > signal_norm:True | > symmetric_norm:True | > mel_fmin:0 | > mel_fmax:8000.0 | > max_norm:4.0 | > clip_norm:True | > do_trim_silence:True | > trim_db:60 | > do_sound_norm:False | > stats_path:None | > hop_length:256 | > win_length:1024 | > n_fft:1024 Using model: Tacotron2 | > Num output units : 513
Model has 28921234 parameters
EPOCH: 0/1000
Number of output frames: 7
DataLoader initialization | > Use phonemes: True | > phoneme language: it | > Number of instances : 75 | > Max length sequence: 380 | > Min length sequence: 2 | > Avg length sequence: 139.69333333333333 | > Num. instances discarded by max-min (max=153, min=6) seq limits: 30 | > Batch group size: 0.
TRAINING (2020-06-05 18:53:25)
--> TRAIN PERFORMACE -- EPOCH TIME: 0 sec -- GLOBAL_STEP: 1 | > avg_postnet_loss: 6.72998 | > avg_decoder_loss: 4.72298 | > avg_stopnet_loss: 0.70530 | > avg_align_error: 0.99250 | > avg_step_time: 17.22977 | > avg_loader_time: 1.13409 | > avg_ga_loss: 0.02929
EVALUATION
Traceback (most recent call last):
File "train.py", line 676, in
can you post config file
can you post config file
`{ "model": "Tacotron2", "run_name": "ljspeech", "run_description": "tacotron2",
// AUDIO PARAMETERS
"audio":{
// stft parameters
"num_freq": 513, // 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. If different than the original data, it is resampled.
"preemphasis": 0.0, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
"ref_level_db": 20, // reference level db, theoretically 20db is the sound of air.
// Silence trimming
"do_trim_silence": true,// enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
"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": 0.0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
"mel_fmax": 8000.0, // maximum freq level for mel-spec. Tune for dataset!!
// 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": null // 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.
"loss_masking": true, // enable / disable loss masking against the sequence padding.
"ga_alpha": 10.0, // weight for guided attention loss. If > 0, guided attention is enabled.
// 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": true, // enable/disable dropout at prenet.
// ATTENTION
"attention_type": "original", // 'original' or 'graves'
"attention_heads": 4, // number of attention heads (only for 'graves')
"attention_norm": "sigmoid", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron.
"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.
// 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 traning on console.
"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": 0, //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
// PATHS
"output_path": "/home/sadam/Projects/Italian_TTS/TTS/Models/LJSpeech/",
// PHONEMES
"phoneme_cache_path": "/home/sadam/Projects/Italian_TTS/TTS/mozilla_us_phonemes_3", // 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": "it", // 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.
"style_wav_for_test": null, // path to style wav file to be used in TacotronGST inference.
"use_gst": false, // TACOTRON ONLY: use global style tokens
// DATASETS
"datasets": // List of datasets. They all merged and they get different speaker_ids.
[
{
"name": "ljspeech",
"path": "/home/sadam/Projects/Italian_TTS/LJSpeech-1.1/",
"meta_file_train": "metadata.csv",
"meta_file_val": null
}
]
}
` Here you go @erogol
Don't ping multiple people, this isn't your personal support agent. And remember it's a weekend.
Don't ping multiple people, this isn't your personal support agent. And remember it's a weekend.
I saw you guys as the active contributors and Eren wasn't replying so I thought....
you have not enough samples. You should have > 100.
you have not enough samples. You should have > 100.
Thank you for clearing that up. :)
! Run is removed from /root/Trainings/ljspeech-stft_params-April-07-2020_10+27AM-fab74dd Traceback (most recent call last): File "train.py", line 724, in main(args) File "train.py", line 641, in main val_loss = evaluate(model, criterion, criterion_st, ap, global_step, File "/root/.pyenv/versions/3.8.2/lib/python3.8/site-packages/torch/autograd/grad_mode.py ", line 49, in decorate_no_grad return func(*args, **kwargs) File "train.py", line 434, in evaluate idx = np.random.randint(mel_input.shape[0]) UnboundLocalError: local variable 'mel_input' referenced before assignment