Upload model, config, vocab and training log

best_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd02035aa2815b805f1db26f4cce42a2cfbe30ca0c4825f432961bc74aa4b420
+size 5607926869

config.json

@@ -0,0 +1,159 @@
+{
+    "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": 6681,
+        "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",
+        "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
+}

trainer_0_log.txt

@@ -0,0 +1,211 @@
+ > Training Environment:
+ | > Backend: Torch
+ | > Mixed precision: False
+ | > Precision: float32
+ | > Current device: 0
+ | > Num. of GPUs: 1
+ | > Num. of CPUs: 2
+ | > Num. of Torch Threads: 1
+ | > Torch seed: 1
+ | > Torch CUDNN: True
+ | > Torch CUDNN deterministic: False
+ | > Torch CUDNN benchmark: False
+ | > Torch TF32 MatMul: False
+ > Start Tensorboard: tensorboard --logdir=/tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000
+
+ > Model has 518442047 parameters
+
+ > EPOCH: 0/8
+ --> /tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000
+
+ > TRAINING (2023-12-04 15:00:11) 
+
+   --> TIME: 2023-12-04 15:00:19 -- STEP: 0/40 -- GLOBAL_STEP: 0
+     | > loss_text_ce: 0.021964602172374725  (0.021964602172374725)
+     | > loss_mel_ce: 4.907757759094238  (4.907757759094238)
+     | > loss: 4.929722309112549  (4.929722309112549)
+     | > grad_norm: 0  (0)
+     | > current_lr: 5e-06 
+     | > step_time: 1.4868  (1.4868354797363281)
+     | > loader_time: 6.5441  (6.544092655181885)
+
+
+ > EVALUATION 
+
+
+  --> EVAL PERFORMANCE
+     | > avg_loader_time: 0.07195439338684081 (+0)
+     | > avg_loss_text_ce: 0.021994752064347266 (+0)
+     | > avg_loss_mel_ce: 3.3762893676757812 (+0)
+     | > avg_loss: 3.398284101486206 (+0)
+
+ > BEST MODEL : /tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000/best_model_40.pth
+
+ > EPOCH: 1/8
+ --> /tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000
+
+ > TRAINING (2023-12-04 15:02:56) 
+
+   --> TIME: 2023-12-04 15:03:03 -- STEP: 10/40 -- GLOBAL_STEP: 50
+     | > loss_text_ce: 0.023661285638809204  (0.023023789189755915)
+     | > loss_mel_ce: 3.8315794467926025  (3.305363488197327)
+     | > loss: 3.855240821838379  (3.328387236595154)
+     | > grad_norm: 0  (0.0)
+     | > current_lr: 5e-06 
+     | > step_time: 0.2479  (0.20201985836029052)
+     | > loader_time: 0.0221  (0.017214274406433104)
+
+
+ > EVALUATION 
+
+
+  --> EVAL PERFORMANCE
+     | > avg_loader_time: 0.1108086109161377 (+0.03885421752929688)
+     | > avg_loss_text_ce: 0.021816403046250342 (-0.00017834901809692452)
+     | > avg_loss_mel_ce: 3.2666261196136475 (-0.10966324806213379)
+     | > avg_loss: 3.288442516326904 (-0.10984158515930176)
+
+ > BEST MODEL : /tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000/best_model_80.pth
+
+ > EPOCH: 2/8
+ --> /tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000
+
+ > TRAINING (2023-12-04 15:06:18) 
+
+   --> TIME: 2023-12-04 15:06:33 -- STEP: 20/40 -- GLOBAL_STEP: 100
+     | > loss_text_ce: 0.017979152500629425  (0.02109259101562202)
+     | > loss_mel_ce: 3.1569440364837646  (2.9896609008312227)
+     | > loss: 3.1749231815338135  (3.0107534766197204)
+     | > grad_norm: 0  (0.0)
+     | > current_lr: 5e-06 
+     | > step_time: 0.1982  (0.25715711116790774)
+     | > loader_time: 0.0208  (0.015216124057769776)
+
+
+ > EVALUATION 
+
+
+  --> EVAL PERFORMANCE
+     | > avg_loader_time: 0.06513414382934571 (-0.04567446708679199)
+     | > avg_loss_text_ce: 0.021773791685700417 (-4.2611360549924676e-05)
+     | > avg_loss_mel_ce: 3.2272082805633544 (-0.03941783905029306)
+     | > avg_loss: 3.248982048034668 (-0.03946046829223615)
+
+ > BEST MODEL : /tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000/best_model_120.pth
+
+ > EPOCH: 3/8
+ --> /tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000
+
+ > TRAINING (2023-12-04 15:10:08) 
+
+   --> TIME: 2023-12-04 15:10:26 -- STEP: 30/40 -- GLOBAL_STEP: 150
+     | > loss_text_ce: 0.021550316363573074  (0.020829477223257224)
+     | > loss_mel_ce: 3.5817322731018066  (2.8207703987757364)
+     | > loss: 3.6032826900482178  (2.8415998578071595)
+     | > grad_norm: 0  (0.0)
+     | > current_lr: 5e-06 
+     | > step_time: 0.2316  (0.26780527432759604)
+     | > loader_time: 0.0088  (0.015432175000508625)
+
+
+ > EVALUATION 
+
+
+  --> EVAL PERFORMANCE
+     | > avg_loader_time: 0.12182736396789551 (+0.0566932201385498)
+     | > avg_loss_text_ce: 0.021623440831899644 (-0.00015035085380077362)
+     | > avg_loss_mel_ce: 3.205338716506958 (-0.021869564056396396)
+     | > avg_loss: 3.226962184906006 (-0.02201986312866211)
+
+ > BEST MODEL : /tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000/best_model_160.pth
+
+ > EPOCH: 4/8
+ --> /tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000
+
+ > TRAINING (2023-12-04 15:13:43) 
+
+ > EVALUATION 
+
+
+  --> EVAL PERFORMANCE
+     | > avg_loader_time: 0.06858286857604981 (-0.0532444953918457)
+     | > avg_loss_text_ce: 0.021538139879703523 (-8.530095219612052e-05)
+     | > avg_loss_mel_ce: 3.19382529258728 (-0.011513423919677912)
+     | > avg_loss: 3.2153634548187258 (-0.011598730087280185)
+
+ > BEST MODEL : /tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000/best_model_200.pth
+
+ > EPOCH: 5/8
+ --> /tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000
+
+ > TRAINING (2023-12-04 15:17:08) 
+
+   --> TIME: 2023-12-04 15:17:10 -- STEP: 0/40 -- GLOBAL_STEP: 200
+     | > loss_text_ce: 0.023776765912771225  (0.023776765912771225)
+     | > loss_mel_ce: 2.0250589847564697  (2.0250589847564697)
+     | > loss: 2.0488357543945312  (2.0488357543945312)
+     | > grad_norm: 0  (0)
+     | > current_lr: 5e-06 
+     | > step_time: 0.9392  (0.9391729831695557)
+     | > loader_time: 1.0643  (1.0642502307891846)
+
+
+ > EVALUATION 
+
+
+  --> EVAL PERFORMANCE
+     | > avg_loader_time: 0.06770339012145996 (-0.0008794784545898549)
+     | > avg_loss_text_ce: 0.02152172140777111 (-1.641847193241397e-05)
+     | > avg_loss_mel_ce: 3.21250319480896 (+0.018677902221679865)
+     | > avg_loss: 3.234024906158447 (+0.018661451339721413)
+
+
+ > EPOCH: 6/8
+ --> /tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000
+
+ > TRAINING (2023-12-04 15:17:31) 
+
+   --> TIME: 2023-12-04 15:17:40 -- STEP: 10/40 -- GLOBAL_STEP: 250
+     | > loss_text_ce: 0.018674146384000778  (0.021112211793661118)
+     | > loss_mel_ce: 2.7348833084106445  (2.436060166358948)
+     | > loss: 2.7535574436187744  (2.457172393798828)
+     | > grad_norm: 0  (0.0)
+     | > current_lr: 5e-06 
+     | > step_time: 0.1765  (0.2836411952972412)
+     | > loader_time: 0.0086  (0.01687464714050293)
+
+
+ > EVALUATION 
+
+
+  --> EVAL PERFORMANCE
+     | > avg_loader_time: 0.06701068878173828 (-0.0006927013397216714)
+     | > avg_loss_text_ce: 0.021476111933588983 (-4.560947418212613e-05)
+     | > avg_loss_mel_ce: 3.206305408477783 (-0.006197786331176847)
+     | > avg_loss: 3.2277815341949463 (-0.006243371963500888)
+
+
+ > EPOCH: 7/8
+ --> /tmp/xtts_ft/run/training/GPT_XTTS_FT-December-04-2023_03+00PM-0000000
+
+ > TRAINING (2023-12-04 15:17:57) 
+
+   --> TIME: 2023-12-04 15:18:11 -- STEP: 20/40 -- GLOBAL_STEP: 300
+     | > loss_text_ce: 0.023174753412604332  (0.019879171112552285)
+     | > loss_mel_ce: 3.1051435470581055  (2.4108093440532685)
+     | > loss: 3.1283183097839355  (2.430688518285751)
+     | > grad_norm: 0  (0.0)
+     | > current_lr: 5e-06 
+     | > step_time: 0.27  (0.29051125049591064)
+     | > loader_time: 0.0138  (0.01517837047576904)
+
+
+ > EVALUATION 
+
+
+  --> EVAL PERFORMANCE
+     | > avg_loader_time: 0.11030998229980468 (+0.0432992935180664)
+     | > avg_loss_text_ce: 0.02148539908230305 (+9.287148714065552e-06)
+     | > avg_loss_mel_ce: 3.223378849029541 (+0.01707344055175808)
+     | > avg_loss: 3.244864273071289 (+0.017082738876342596)
+