Upload 25 files

.gitattributes

@@ -109,3 +109,15 @@ xtts-v2/eng/MelinaEldenRing/MelinaEldenRing_generated_example.wav filter=lfs dif
 xtts-v2/eng/MelinaEldenRing/MelinaEldenRing.wav filter=lfs diff=lfs merge=lfs -text
 xtts-v2/eng/MelinaEldenRing/reference.wav filter=lfs diff=lfs merge=lfs -text
 xtts-v2/eng/MelinaEldenRing/TrainingDataMelinaEldenRing.mp3 filter=lfs diff=lfs merge=lfs -text
+xtts-v2/eng/GideonOfnirEldenRing/GideonOfnirEldenRing_16000.wav filter=lfs diff=lfs merge=lfs -text
+xtts-v2/eng/GideonOfnirEldenRing/GideonOfnirEldenRing_24000.wav filter=lfs diff=lfs merge=lfs -text
+xtts-v2/eng/GideonOfnirEldenRing/GideonOfnirEldenRing_generated_example.wav filter=lfs diff=lfs merge=lfs -text
+xtts-v2/eng/GideonOfnirEldenRing/GideonOfnirEldenRing.wav filter=lfs diff=lfs merge=lfs -text
+xtts-v2/eng/JuliaWhenlan/JuliaWhenlan_16000.wav filter=lfs diff=lfs merge=lfs -text
+xtts-v2/eng/JuliaWhenlan/JuliaWhenlan_24000.wav filter=lfs diff=lfs merge=lfs -text
+xtts-v2/eng/JuliaWhenlan/JuliaWhenlan_generated_example.wav filter=lfs diff=lfs merge=lfs -text
+xtts-v2/eng/JuliaWhenlan/JuliaWhenlan.wav filter=lfs diff=lfs merge=lfs -text
+xtts-v2/eng/NeilGaiman/NeilGaiman_16000.wav filter=lfs diff=lfs merge=lfs -text
+xtts-v2/eng/NeilGaiman/NeilGaiman_24000.wav filter=lfs diff=lfs merge=lfs -text
+xtts-v2/eng/NeilGaiman/NeilGaiman_generated_example.wav filter=lfs diff=lfs merge=lfs -text
+xtts-v2/eng/NeilGaiman/NeilGaiman.wav filter=lfs diff=lfs merge=lfs -text

xtts-v2/eng/GideonOfnirEldenRing/GideonOfnirEldenRing.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd335d72647ff8230ee9cfbe302c611a92ef6649d0beee0bfa4181b6cde4fd5
+size 12465678

xtts-v2/eng/GideonOfnirEldenRing/GideonOfnirEldenRing_16000.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d52237b580fe6333207cf2ee369d3d19884ba95c20daa5dcdb7bf21c5dea61
+size 480078

xtts-v2/eng/GideonOfnirEldenRing/GideonOfnirEldenRing_24000.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30870a09105dde500c4bf0f6bf12573df4d86b4a95c6ec80f1b8e6990fd52f8e
+size 720078

xtts-v2/eng/GideonOfnirEldenRing/GideonOfnirEldenRing_generated_example.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0208d7965b570c5a12450fb95a76a95184809de9c3792b4430e9fc73a13371
+size 267342

xtts-v2/eng/GideonOfnirEldenRing/config.json

@@ -0,0 +1,158 @@
+{
+    "output_path": "output",
+    "logger_uri": null,
+    "run_name": "run",
+    "project_name": null,
+    "run_description": "\ud83d\udc38Coqui trainer run.",
+    "print_step": 25,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "save_on_interrupt": true,
+    "log_model_step": null,
+    "save_step": 10000,
+    "save_n_checkpoints": 5,
+    "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": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 16,
+    "grad_clip": 0.0,
+    "scheduler_after_epoch": true,
+    "lr": 0.001,
+    "optimizer": "radam",
+    "optimizer_params": null,
+    "lr_scheduler": null,
+    "lr_scheduler_params": {},
+    "use_grad_scaler": false,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "xtts",
+    "num_loader_workers": 0,
+    "num_eval_loader_workers": 0,
+    "use_noise_augment": false,
+    "audio": {
+        "sample_rate": 22050,
+        "output_sample_rate": 24000
+    },
+    "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": Infinity,
+    "min_text_len": 1,
+    "max_text_len": Infinity,
+    "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": null,
+    "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": null,
+        "clvp_checkpoint": null,
+        "decoder_checkpoint": null,
+        "num_chars": 255,
+        "tokenizer_file": "",
+        "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": 6153,
+        "gpt_start_text_token": null,
+        "gpt_stop_text_token": null,
+        "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
+    },
+    "model_dir": null,
+    "languages": [
+        "en",
+        "es",
+        "fr",
+        "de",
+        "it",
+        "pt",
+        "pl",
+        "tr",
+        "ru",
+        "nl",
+        "cs",
+        "ar",
+        "zh-cn",
+        "hu",
+        "ko",
+        "ja"
+    ],
+    "temperature": 0.75,
+    "length_penalty": 1.0,
+    "repetition_penalty": 10.0,
+    "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
+}

xtts-v2/eng/GideonOfnirEldenRing/dataset.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47bddf06e88fa03483e57fc9262c4e4da6097134aa5466a411d5d8143a2085bb
+size 71507416

xtts-v2/eng/GideonOfnirEldenRing/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359ce1c1b81f5e63892a89faa83f1c755ac039c9e65b2d4c4e7a0a8dd87805b9
+size 1863948502

xtts-v2/eng/GideonOfnirEldenRing/speakers_xtts.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f6137c19a4eab0cbbe4c99b5babacf68b1746e50da90807708c10e645b943b
+size 7754818

xtts-v2/eng/JuliaWhenlan/JuliaWhenlan.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e6eddd32e5ca7a6002a2503486927898019947a79961dd1e57612d442335f2
+size 15194958

xtts-v2/eng/JuliaWhenlan/JuliaWhenlan_16000.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b184e8858c5380e23d22eb7b294bab39ed1cb4dda497f322d46c0cd93c54117
+size 480078

xtts-v2/eng/JuliaWhenlan/JuliaWhenlan_24000.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86291b4b7231e5548f91302789e966ddec0114e655e34963b96bf0eddf22b97e
+size 720078

xtts-v2/eng/JuliaWhenlan/JuliaWhenlan_generated_example.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf4fd2a87e9ae05c8c1c4fa87ecd45cf55983022a9de74df4416c23e325fd745
+size 204878

xtts-v2/eng/JuliaWhenlan/config.json

@@ -0,0 +1,158 @@
+{
+    "output_path": "output",
+    "logger_uri": null,
+    "run_name": "run",
+    "project_name": null,
+    "run_description": "\ud83d\udc38Coqui trainer run.",
+    "print_step": 25,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "save_on_interrupt": true,
+    "log_model_step": null,
+    "save_step": 10000,
+    "save_n_checkpoints": 5,
+    "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": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 16,
+    "grad_clip": 0.0,
+    "scheduler_after_epoch": true,
+    "lr": 0.001,
+    "optimizer": "radam",
+    "optimizer_params": null,
+    "lr_scheduler": null,
+    "lr_scheduler_params": {},
+    "use_grad_scaler": false,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "xtts",
+    "num_loader_workers": 0,
+    "num_eval_loader_workers": 0,
+    "use_noise_augment": false,
+    "audio": {
+        "sample_rate": 22050,
+        "output_sample_rate": 24000
+    },
+    "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": Infinity,
+    "min_text_len": 1,
+    "max_text_len": Infinity,
+    "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": null,
+    "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": null,
+        "clvp_checkpoint": null,
+        "decoder_checkpoint": null,
+        "num_chars": 255,
+        "tokenizer_file": "",
+        "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": 6153,
+        "gpt_start_text_token": null,
+        "gpt_stop_text_token": null,
+        "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
+    },
+    "model_dir": null,
+    "languages": [
+        "en",
+        "es",
+        "fr",
+        "de",
+        "it",
+        "pt",
+        "pl",
+        "tr",
+        "ru",
+        "nl",
+        "cs",
+        "ar",
+        "zh-cn",
+        "hu",
+        "ko",
+        "ja"
+    ],
+    "temperature": 0.75,
+    "length_penalty": 1.0,
+    "repetition_penalty": 10.0,
+    "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
+}

xtts-v2/eng/JuliaWhenlan/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53ff6ccf219308f622e35aa6872f882f310ac378b733108d68e1354a4ffaaad7
+size 1863948502

xtts-v2/eng/JuliaWhenlan/speakers_xtts.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f6137c19a4eab0cbbe4c99b5babacf68b1746e50da90807708c10e645b943b
+size 7754818

xtts-v2/eng/NeilGaiman/NeilGaiman.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b541e01261de1df70f1963333a832e576aa79f00d3892959f536327f31cf3ba
+size 1880718

xtts-v2/eng/NeilGaiman/NeilGaiman_16000.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0f96e4cdc5d550148623194833f34bd1e258772ea675a35f998940070cc5de
+size 626958

xtts-v2/eng/NeilGaiman/NeilGaiman_24000.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73859c0ac41490fd5a421609354f82af1dfea3db10b0f386dd8710e5962c5810
+size 940398

xtts-v2/eng/NeilGaiman/NeilGaiman_generated_example.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c690917be805eeefdf4f44c3d53c5613bd099f7d8aa54053bb1954232a88a35d
+size 240718

xtts-v2/eng/NeilGaiman/config.json

@@ -0,0 +1,158 @@
+{
+    "output_path": "output",
+    "logger_uri": null,
+    "run_name": "run",
+    "project_name": null,
+    "run_description": "\ud83d\udc38Coqui trainer run.",
+    "print_step": 25,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "save_on_interrupt": true,
+    "log_model_step": null,
+    "save_step": 10000,
+    "save_n_checkpoints": 5,
+    "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": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 16,
+    "grad_clip": 0.0,
+    "scheduler_after_epoch": true,
+    "lr": 0.001,
+    "optimizer": "radam",
+    "optimizer_params": null,
+    "lr_scheduler": null,
+    "lr_scheduler_params": {},
+    "use_grad_scaler": false,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "xtts",
+    "num_loader_workers": 0,
+    "num_eval_loader_workers": 0,
+    "use_noise_augment": false,
+    "audio": {
+        "sample_rate": 22050,
+        "output_sample_rate": 24000
+    },
+    "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": Infinity,
+    "min_text_len": 1,
+    "max_text_len": Infinity,
+    "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": null,
+    "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": null,
+        "clvp_checkpoint": null,
+        "decoder_checkpoint": null,
+        "num_chars": 255,
+        "tokenizer_file": "",
+        "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": 6153,
+        "gpt_start_text_token": null,
+        "gpt_stop_text_token": null,
+        "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
+    },
+    "model_dir": null,
+    "languages": [
+        "en",
+        "es",
+        "fr",
+        "de",
+        "it",
+        "pt",
+        "pl",
+        "tr",
+        "ru",
+        "nl",
+        "cs",
+        "ar",
+        "zh-cn",
+        "hu",
+        "ko",
+        "ja"
+    ],
+    "temperature": 0.75,
+    "length_penalty": 1.0,
+    "repetition_penalty": 10.0,
+    "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
+}

xtts-v2/eng/NeilGaiman/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c46cc91758939a3de669aa5cada437e496a425e67e15b9ba037a0373485b751
+size 1863948502

xtts-v2/eng/NeilGaiman/speakers_xtts.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f6137c19a4eab0cbbe4c99b5babacf68b1746e50da90807708c10e645b943b
+size 7754818