mirror of https://github.com/coqui-ai/TTS.git
956 lines
37 KiB
JSON
956 lines
37 KiB
JSON
{
|
|
"model": "speaker_encoder",
|
|
"run_name": "speaker_encoder",
|
|
"run_description": "resnet speaker encoder trained with commonvoice all languages dev and train, Voxceleb 1 dev and Voxceleb 2 dev",
|
|
// AUDIO PARAMETERS
|
|
"audio":{
|
|
// Audio processing parameters
|
|
"num_mels": 80, // size of the mel spec frame.
|
|
"fft_size": 1024, // number of stft frequency levels. Size of the linear spectogram frame.
|
|
"sample_rate": 16000, // 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.
|
|
"stft_pad_mode": "reflect",
|
|
// 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!!
|
|
"spec_gain": 20.0,
|
|
"do_trim_silence": false, // 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.
|
|
"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
|
|
},
|
|
"reinit_layers": [],
|
|
|
|
"loss": "angleproto", // "ge2e" to use Generalized End-to-End loss, "angleproto" to use Angular Prototypical loss and "softmaxproto" to use Softmax with Angular Prototypical loss
|
|
"grad_clip": 3.0, // upper limit for gradients for clipping.
|
|
"max_train_step": 1000000, // total number of steps to train.
|
|
"lr": 0.0001, // Initial learning rate. If Noam decay is active, maximum learning rate.
|
|
"lr_decay": false, // if true, Noam learning rate decaying is applied through training.
|
|
"warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr"
|
|
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
|
|
"steps_plot_stats": 100, // number of steps to plot embeddings.
|
|
|
|
// Speakers config
|
|
"num_speakers_in_batch": 200, // Batch size for training.
|
|
"num_utters_per_speaker": 2, //
|
|
"skip_speakers": true, // skip speakers with samples less than "num_utters_per_speaker"
|
|
"voice_len": 2, // number of seconds for each training instance
|
|
|
|
"num_loader_workers": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values.
|
|
"wd": 0.000001, // Weight decay weight.
|
|
"checkpoint": true, // If true, it saves checkpoints per "save_step"
|
|
"save_step": 1000, // Number of training steps expected to save the best checkpoints in training.
|
|
"print_step": 50, // Number of steps to log traning on console.
|
|
"output_path": "../checkpoints/speaker_encoder/angleproto/resnet_voxceleb1_and_voxceleb2-and-common-voice-all-using-angleproto/", // DATASET-RELATED: output path for all training outputs.
|
|
|
|
"audio_augmentation": {
|
|
"p": 0.5, // propability of apply this method, 0 is disable rir and additive noise augmentation
|
|
"rir":{
|
|
"rir_path": "/workspace/store/ecasanova/ComParE/RIRS_NOISES/simulated_rirs/",
|
|
"conv_mode": "full"
|
|
},
|
|
"additive":{
|
|
"sounds_path": "/workspace/store/ecasanova/ComParE/musan/",
|
|
// list of each of the directories in your data augmentation, if a directory is in "sounds_path" but is not listed here it will be ignored
|
|
"speech":{
|
|
"min_snr_in_db": 13,
|
|
"max_snr_in_db": 20,
|
|
"min_num_noises": 2,
|
|
"max_num_noises": 3
|
|
},
|
|
"noise":{
|
|
"min_snr_in_db": 0,
|
|
"max_snr_in_db": 15,
|
|
"min_num_noises": 1,
|
|
"max_num_noises": 1
|
|
},
|
|
"music":{
|
|
"min_snr_in_db": 5,
|
|
"max_snr_in_db": 15,
|
|
"min_num_noises": 1,
|
|
"max_num_noises": 1
|
|
}
|
|
},
|
|
//add a gaussian noise to the data in order to increase robustness
|
|
"gaussian":{ // as the insertion of Gaussian noise is quick to be calculated, we added it after loading the wav file, this way, even audios that were reused with the cache can receive this noise
|
|
"p": 0.5, // propability of apply this method, 0 is disable
|
|
"min_amplitude": 0.0,
|
|
"max_amplitude": 1e-5
|
|
}
|
|
},
|
|
"model_params": {
|
|
"model_name": "resnet",
|
|
"input_dim": 80,
|
|
"proj_dim": 512
|
|
},
|
|
"storage": {
|
|
"sample_from_storage_p": 0.5, // the probability with which we'll sample from the DataSet in-memory storage
|
|
"storage_size": 35 // the size of the in-memory storage with respect to a single batch
|
|
},
|
|
"datasets":
|
|
[
|
|
{
|
|
"name": "voxceleb2",
|
|
"path": "/workspace/scratch/ecasanova/datasets/VoxCeleb/vox2_dev_aac/",
|
|
"meta_file_train": null,
|
|
"meta_file_val": null
|
|
},
|
|
{
|
|
"name": "voxceleb1",
|
|
"path": "/workspace/scratch/ecasanova/datasets/VoxCeleb/vox1_dev_wav/",
|
|
"meta_file_train": null,
|
|
"meta_file_val": null
|
|
},
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/fi",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/fi",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/zh-CN",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/zh-CN",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/rm-sursilv",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/rm-sursilv",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/lt",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/lt",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ka",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ka",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/sv-SE",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/sv-SE",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/pl",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/pl",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ru",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ru",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/mn",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/mn",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/nl",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/nl",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/sl",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/sl",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/es",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/es",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/pt",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/pt",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/hi",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/hi",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ja",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ja",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ia",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ia",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/br",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/br",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/id",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/id",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/dv",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/dv",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ta",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ta",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/or",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/or",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/zh-HK",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/zh-HK",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/de",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/de",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/uk",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/uk",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/en",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/en",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/fa",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/fa",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/vi",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/vi",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ab",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ab",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/sah",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/sah",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/vot",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/vot",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/fr",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/fr",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/tr",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/tr",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/lg",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/lg",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/mt",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/mt",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/rw",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/rw",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/hu",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/hu",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/rm-vallader",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/rm-vallader",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/el",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/el",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/tt",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/tt",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/zh-TW",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/zh-TW",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/et",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/et",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/fy-NL",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/fy-NL",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/cs",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/cs",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/as",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/as",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ro",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ro",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/eo",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/eo",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/pa-IN",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/pa-IN",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/th",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/th",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/it",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/it",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ga-IE",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ga-IE",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/cnh",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/cnh",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ky",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ky",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ar",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ar",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/eu",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/eu",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ca",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/ca",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/kab",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/kab",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/cy",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/cy",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/cv",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/cv",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/hsb",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/hsb",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/lv",
|
|
"meta_file_train": "train.tsv",
|
|
"meta_file_val": null
|
|
},
|
|
|
|
{
|
|
"name": "common_voice",
|
|
"path": "/workspace/scratch/ecasanova/datasets/common-voice/cv-corpus-6.1-2020-12-11_16khz/lv",
|
|
"meta_file_train": "dev.tsv",
|
|
"meta_file_val": null
|
|
}
|
|
|
|
]
|
|
} |