Add 'ig' to supported languages in config.json

config.json

@@ -1,192 +1,193 @@
 {
-    "output_path": "/checkpoints/ig/checkpoints_commonvoice/",
-    "logger_uri": null,
-    "run_name": "GPT_XTTS_FT",
-    "project_name": "XTTS_trainer",
-    "run_description": [
-        "\n        GPT XTTS training\n        "
+  "output_path": "/checkpoints/ig/checkpoints_commonvoice/",
+  "logger_uri": null,
+  "run_name": "GPT_XTTS_FT",
+  "project_name": "XTTS_trainer",
+  "run_description": [
+    "\n        GPT XTTS training\n        "
+  ],
+  "print_step": 50,
+  "plot_step": 100,
+  "model_param_stats": false,
+  "wandb_entity": null,
+  "dashboard_logger": "tensorboard",
+  "save_on_interrupt": true,
+  "log_model_step": 100,
+  "save_step": 300,
+  "save_n_checkpoints": 1,
+  "save_checkpoints": true,
+  "save_all_best": false,
+  "save_best_after": 10000,
+  "target_loss": null,
+  "print_eval": false,
+  "test_delay_epochs": 0,
+  "run_eval": true,
+  "run_eval_steps": null,
+  "distributed_backend": "nccl",
+  "distributed_url": "tcp://localhost:54321",
+  "mixed_precision": false,
+  "precision": "fp16",
+  "epochs": 4,
+  "batch_size": 2,
+  "eval_batch_size": 16,
+  "grad_clip": 0.0,
+  "scheduler_after_epoch": true,
+  "lr": 1.5e-06,
+  "optimizer": "AdamW",
+  "optimizer_params": {
+    "betas": [
+      0.9,
+      0.96
     ],
-    "print_step": 50,
-    "plot_step": 100,
-    "model_param_stats": false,
-    "wandb_entity": null,
-    "dashboard_logger": "tensorboard",
-    "save_on_interrupt": true,
-    "log_model_step": 100,
-    "save_step": 300,
-    "save_n_checkpoints": 1,
-    "save_checkpoints": true,
-    "save_all_best": false,
-    "save_best_after": 10000,
-    "target_loss": null,
-    "print_eval": false,
-    "test_delay_epochs": 0,
-    "run_eval": true,
-    "run_eval_steps": null,
-    "distributed_backend": "nccl",
-    "distributed_url": "tcp://localhost:54321",
-    "mixed_precision": false,
-    "precision": "fp16",
-    "epochs": 4,
-    "batch_size": 2,
-    "eval_batch_size": 16,
-    "grad_clip": 0.0,
-    "scheduler_after_epoch": true,
-    "lr": 1.5e-06,
-    "optimizer": "AdamW",
-    "optimizer_params": {
-        "betas": [
-            0.9,
-            0.96
-        ],
-        "eps": 1e-08,
-        "weight_decay": 0.01
-    },
-    "lr_scheduler": "MultiStepLR",
-    "lr_scheduler_params": {
-        "milestones": [
-            900000,
-            2700000,
-            5400000
-        ],
-        "gamma": 0.5,
-        "last_epoch": -1
-    },
-    "use_grad_scaler": false,
-    "allow_tf32": false,
-    "cudnn_enable": true,
-    "cudnn_deterministic": false,
-    "cudnn_benchmark": false,
-    "training_seed": 54321,
-    "model": "xtts",
-    "num_loader_workers": 8,
-    "num_eval_loader_workers": 0,
-    "use_noise_augment": false,
-    "audio": {
-        "sample_rate": 22050,
-        "output_sample_rate": 24000,
-        "dvae_sample_rate": 22050
-    },
-    "use_phonemes": false,
-    "phonemizer": null,
-    "phoneme_language": null,
-    "compute_input_seq_cache": false,
-    "text_cleaner": null,
-    "enable_eos_bos_chars": false,
-    "test_sentences_file": "",
-    "phoneme_cache_path": null,
-    "characters": null,
-    "add_blank": false,
-    "batch_group_size": 0,
-    "loss_masking": null,
-    "min_audio_len": 1,
-    "max_audio_len": null,
-    "min_text_len": 1,
-    "max_text_len": null,
-    "compute_f0": false,
-    "compute_energy": false,
-    "compute_linear_spec": false,
-    "precompute_num_workers": 0,
-    "start_by_longest": false,
-    "shuffle": false,
-    "drop_last": false,
-    "datasets": [
-        {
-            "formatter": "",
-            "dataset_name": "",
-            "path": "",
-            "meta_file_train": "",
-            "ignored_speakers": null,
-            "language": "",
-            "phonemizer": "",
-            "meta_file_val": "",
-            "meta_file_attn_mask": ""
-        }
+    "eps": 1e-08,
+    "weight_decay": 0.01
+  },
+  "lr_scheduler": "MultiStepLR",
+  "lr_scheduler_params": {
+    "milestones": [
+      900000,
+      2700000,
+      5400000
     ],
-    "test_sentences": [],
-    "eval_split_max_size": 256,
-    "eval_split_size": 0.01,
-    "use_speaker_weighted_sampler": false,
-    "speaker_weighted_sampler_alpha": 1.0,
-    "use_language_weighted_sampler": false,
-    "language_weighted_sampler_alpha": 1.0,
-    "use_length_weighted_sampler": false,
-    "length_weighted_sampler_alpha": 1.0,
-    "model_args": {
-        "gpt_batch_size": 1,
-        "enable_redaction": false,
-        "kv_cache": true,
-        "gpt_checkpoint": "",
-        "clvp_checkpoint": null,
-        "decoder_checkpoint": null,
-        "num_chars": 255,
-        "tokenizer_file": "/checkpoints/ig/checkpoints_commonvoice/XTTS_v2.0_original_model_files/vocab.json",
-        "gpt_max_audio_tokens": 605,
-        "gpt_max_text_tokens": 402,
-        "gpt_max_prompt_tokens": 70,
-        "gpt_layers": 30,
-        "gpt_n_model_channels": 1024,
-        "gpt_n_heads": 16,
-        "gpt_number_text_tokens": 11533,
-        "gpt_start_text_token": 261,
-        "gpt_stop_text_token": 0,
-        "gpt_num_audio_tokens": 1026,
-        "gpt_start_audio_token": 1024,
-        "gpt_stop_audio_token": 1025,
-        "gpt_code_stride_len": 1024,
-        "gpt_use_masking_gt_prompt_approach": true,
-        "gpt_use_perceiver_resampler": true,
-        "input_sample_rate": 22050,
-        "output_sample_rate": 24000,
-        "output_hop_length": 256,
-        "decoder_input_dim": 1024,
-        "d_vector_dim": 512,
-        "cond_d_vector_in_each_upsampling_layer": true,
-        "duration_const": 102400,
-        "min_conditioning_length": 11025,
-        "max_conditioning_length": 132300,
-        "gpt_loss_text_ce_weight": 0.01,
-        "gpt_loss_mel_ce_weight": 1.0,
-        "debug_loading_failures": false,
-        "max_wav_length": 330750,
-        "max_text_length": 400,
-        "mel_norm_file": "/checkpoints/ig/checkpoints_commonvoice/XTTS_v2.0_original_model_files/mel_stats.pth",
-        "dvae_checkpoint": "/checkpoints/ig/checkpoints_commonvoice/XTTS_v2.0_original_model_files/dvae.pth",
-        "xtts_checkpoint": "/checkpoints/ig/checkpoints_commonvoice/XTTS_v2.0_original_model_files/model.pth",
-        "vocoder": ""
-    },
-    "model_dir": null,
-    "languages": [
-        "en",
-        "es",
-        "fr",
-        "de",
-        "it",
-        "pt",
-        "pl",
-        "tr",
-        "ru",
-        "nl",
-        "cs",
-        "ar",
-        "zh-cn",
-        "hu",
-        "ko",
-        "ja",
-        "hi"
-    ],
-    "temperature": 0.75,
-    "length_penalty": 1.0,
-    "repetition_penalty": 5.0,
-    "top_k": 50,
-    "top_p": 0.85,
-    "num_gpt_outputs": 1,
-    "gpt_cond_len": 30,
-    "gpt_cond_chunk_len": 4,
-    "max_ref_len": 30,
-    "sound_norm_refs": false,
-    "optimizer_wd_only_on_weights": true,
-    "weighted_loss_attrs": null,
-    "weighted_loss_multipliers": null,
-    "github_branch": "* main"
+    "gamma": 0.5,
+    "last_epoch": -1
+  },
+  "use_grad_scaler": false,
+  "allow_tf32": false,
+  "cudnn_enable": true,
+  "cudnn_deterministic": false,
+  "cudnn_benchmark": false,
+  "training_seed": 54321,
+  "model": "xtts",
+  "num_loader_workers": 8,
+  "num_eval_loader_workers": 0,
+  "use_noise_augment": false,
+  "audio": {
+    "sample_rate": 22050,
+    "output_sample_rate": 24000,
+    "dvae_sample_rate": 22050
+  },
+  "use_phonemes": false,
+  "phonemizer": null,
+  "phoneme_language": null,
+  "compute_input_seq_cache": false,
+  "text_cleaner": null,
+  "enable_eos_bos_chars": false,
+  "test_sentences_file": "",
+  "phoneme_cache_path": null,
+  "characters": null,
+  "add_blank": false,
+  "batch_group_size": 0,
+  "loss_masking": null,
+  "min_audio_len": 1,
+  "max_audio_len": null,
+  "min_text_len": 1,
+  "max_text_len": null,
+  "compute_f0": false,
+  "compute_energy": false,
+  "compute_linear_spec": false,
+  "precompute_num_workers": 0,
+  "start_by_longest": false,
+  "shuffle": false,
+  "drop_last": false,
+  "datasets": [
+    {
+      "formatter": "",
+      "dataset_name": "",
+      "path": "",
+      "meta_file_train": "",
+      "ignored_speakers": null,
+      "language": "",
+      "phonemizer": "",
+      "meta_file_val": "",
+      "meta_file_attn_mask": ""
+    }
+  ],
+  "test_sentences": [],
+  "eval_split_max_size": 256,
+  "eval_split_size": 0.01,
+  "use_speaker_weighted_sampler": false,
+  "speaker_weighted_sampler_alpha": 1.0,
+  "use_language_weighted_sampler": false,
+  "language_weighted_sampler_alpha": 1.0,
+  "use_length_weighted_sampler": false,
+  "length_weighted_sampler_alpha": 1.0,
+  "model_args": {
+    "gpt_batch_size": 1,
+    "enable_redaction": false,
+    "kv_cache": true,
+    "gpt_checkpoint": "",
+    "clvp_checkpoint": null,
+    "decoder_checkpoint": null,
+    "num_chars": 255,
+    "tokenizer_file": "/checkpoints/ig/checkpoints_commonvoice/XTTS_v2.0_original_model_files/vocab.json",
+    "gpt_max_audio_tokens": 605,
+    "gpt_max_text_tokens": 402,
+    "gpt_max_prompt_tokens": 70,
+    "gpt_layers": 30,
+    "gpt_n_model_channels": 1024,
+    "gpt_n_heads": 16,
+    "gpt_number_text_tokens": 11533,
+    "gpt_start_text_token": 261,
+    "gpt_stop_text_token": 0,
+    "gpt_num_audio_tokens": 1026,
+    "gpt_start_audio_token": 1024,
+    "gpt_stop_audio_token": 1025,
+    "gpt_code_stride_len": 1024,
+    "gpt_use_masking_gt_prompt_approach": true,
+    "gpt_use_perceiver_resampler": true,
+    "input_sample_rate": 22050,
+    "output_sample_rate": 24000,
+    "output_hop_length": 256,
+    "decoder_input_dim": 1024,
+    "d_vector_dim": 512,
+    "cond_d_vector_in_each_upsampling_layer": true,
+    "duration_const": 102400,
+    "min_conditioning_length": 11025,
+    "max_conditioning_length": 132300,
+    "gpt_loss_text_ce_weight": 0.01,
+    "gpt_loss_mel_ce_weight": 1.0,
+    "debug_loading_failures": false,
+    "max_wav_length": 330750,
+    "max_text_length": 400,
+    "mel_norm_file": "/checkpoints/ig/checkpoints_commonvoice/XTTS_v2.0_original_model_files/mel_stats.pth",
+    "dvae_checkpoint": "/checkpoints/ig/checkpoints_commonvoice/XTTS_v2.0_original_model_files/dvae.pth",
+    "xtts_checkpoint": "/checkpoints/ig/checkpoints_commonvoice/XTTS_v2.0_original_model_files/model.pth",
+    "vocoder": ""
+  },
+  "model_dir": null,
+  "languages": [
+    "en",
+    "es",
+    "fr",
+    "de",
+    "it",
+    "pt",
+    "pl",
+    "tr",
+    "ru",
+    "nl",
+    "cs",
+    "ar",
+    "zh-cn",
+    "hu",
+    "ko",
+    "ja",
+    "hi",
+    "ig"
+  ],
+  "temperature": 0.75,
+  "length_penalty": 1.0,
+  "repetition_penalty": 5.0,
+  "top_k": 50,
+  "top_p": 0.85,
+  "num_gpt_outputs": 1,
+  "gpt_cond_len": 30,
+  "gpt_cond_chunk_len": 4,
+  "max_ref_len": 30,
+  "sound_norm_refs": false,
+  "optimizer_wd_only_on_weights": true,
+  "weighted_loss_attrs": null,
+  "weighted_loss_multipliers": null,
+  "github_branch": "* main"
 }