wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-11 12:00:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactoring tests after Coqpit

Browse Source
This commit is contained in:
Eren Gölge
2021-05-11 11:30:00 +02:00
parent 87384c6008
commit 5aee30443f
29 changed files with 156 additions and 153 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/inputs/test_config.json
+26 -26
View File
@@ -1,24 +1,24 @@
{
"audio":{
"audio_processor": "audio", // to use dictate different audio processors, if available.
"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": 22050, // wav sample-rate. If different than the original data, it is resampled.
"frame_length_ms": null, // stft window length in ms.
"frame_shift_ms": null, // stft window hop-lengh in ms.
"audio_processor": "audio",
"num_mels": 80,
"fft_size": 1024,
"sample_rate": 22050,
"frame_length_ms": null,
"frame_shift_ms": null,
"hop_length": 256,
"win_length": 1024,
"preemphasis": 0.97, // 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": 30,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation.
"signal_norm": true, // normalize the spec values in range [0, 1]
"symmetric_norm": true, // move normalization to range [-1, 1]
"clip_norm": true, // clip normalized values into the range.
"max_norm": 4, // scale normalization to range [-max_norm, max_norm] or [0, max_norm]
"mel_fmin": 0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
"mel_fmax": 8000, // maximum freq level for mel-spec. Tune for dataset!!
"preemphasis": 0.97,
"min_level_db": -100,
"ref_level_db": 20,
"power": 1.5,
"griffin_lim_iters": 30,
"signal_norm": true,
"symmetric_norm": true,
"clip_norm": true,
"max_norm": 4,
"mel_fmin": 0,
"mel_fmax": 8000,
"do_trim_silence": false,
"spec_gain": 20
},
@@ -53,15 +53,15 @@
"max_seq_len": 300,
"log_dir": "tests/outputs/",
// MULTI-SPEAKER and GST
"use_speaker_embedding": false, // use speaker embedding to enable multi-speaker learning.
"use_gst": true, // use global style tokens
"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_num_style_tokens).
"gst_use_speaker_embedding": true, // if true pass speaker embedding in attention input GST.
"use_speaker_embedding": false,
"use_gst": true,
"gst": {
"gst_style_input": null,
"gst_use_speaker_embedding": true,
"gst_embedding_dim": 512,
"gst_num_heads": 4,
"gst_num_style_tokens": 10
tests/inputs/test_speaker_encoder_config.json
+3 -1
View File
@@ -1,5 +1,6 @@
{
"model": "speaker_encoder",
"run_name": "test_speaker_encoder",
"run_description": "test speaker encoder.",
"audio":{
@@ -42,8 +43,9 @@
"checkpoint": true, // If true, it saves checkpoints per "save_step"
"save_step": 1000, // Number of training steps expected to save traning stats and checkpoints.
"print_step": 20, // Number of steps to log traning on console.
"batch_size": 32,
"output_path": "", // DATASET-RELATED: output path for all training outputs.
"model": {
"model_params": {
"input_dim": 40,
"proj_dim": 256,
"lstm_dim": 768,