Upload 15 files

.gitattributes

@@ -33,3 +33,14 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+samples/nam-calm.wav filter=lfs diff=lfs merge=lfs -text
+samples/nam-cham.wav filter=lfs diff=lfs merge=lfs -text
+samples/nam-nhanh.wav filter=lfs diff=lfs merge=lfs -text
+samples/nam-truyen-cam.wav filter=lfs diff=lfs merge=lfs -text
+samples/nu-calm.wav filter=lfs diff=lfs merge=lfs -text
+samples/nu-cham.wav filter=lfs diff=lfs merge=lfs -text
+samples/nu-luu-loat.wav filter=lfs diff=lfs merge=lfs -text
+samples/nu-nhan-nha.wav filter=lfs diff=lfs merge=lfs -text
+samples/nu-nhe-nhang.wav filter=lfs diff=lfs merge=lfs -text
+user_sample.wav filter=lfs diff=lfs merge=lfs -text
+vi_sample.wav filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,49 @@
 ---
-license: apache-2.0
+license: other
+license_name: coqui-public-model-license
+license_link: https://coqui.ai/cpml
+pipeline_tag: text-to-speech
+datasets:
+- capleaf/viVoice
+language:
+- vi
 ---
+
+# viⓍTTS
+
+viⓍTTS là mô hình tạo sinh giọng nói cho phép bạn sao chép giọng nói sang các ngôn ngữ khác nhau chỉ bằng cách sử dụng một đoạn âm thanh nhanh dài 6 giây. Mô hình này được tiếp tục đào tạo từ mô hình [XTTS-v2.0.3](https://huggingface.co/coqui/XTTS-v2) bằng cách mở rộng tokenizer sang tiếng Việt và huấn luyện trên tập dữ liệu [viVoice](https://huggingface.co/datasets/thinhlpg/viVoice).
+
+viⓍTTS is a voice generation model that lets you clone voices into different languages by using just a quick 6-second audio clip. This model is fine-tuned from the [XTTS-v2.0.3](https://huggingface.co/coqui/XTTS-v2) model by expanding the tokenizer to Vietnamese and fine-tuning on the [viVoice](https://huggingface.co/datasets/thinhlpg/viVoice) dataset.
+
+### Languages
+
+viXTTS supports 18 languages: English (en), Spanish (es), French (fr), German (de), Italian (it), Portuguese (pt),
+Polish (pl), Turkish (tr), Russian (ru), Dutch (nl), Czech (cs), Arabic (ar), Chinese (zh-cn), Japanese (ja), Hungarian (hu), Korean (ko)
+Hindi (hi), **Vietnamese (vi)**.
+
+### Known Limitations
+
+- Incompatibility with the [original TTS library](https://github.com/coqui-ai/TTS) (a pull request will be made later).
+- Subpar performance for input sentences under 10 words in Vietnamese language (yielding inconsistent output and odd trailing sounds).
+- This model is only fine-tuned in Vietnamese. The model's effectiveness with languages other than Vietnamese hasn't been tested, potentially reducing quality.
+  
+### Demo
+
+Please checkout [this repo](https://github.com/thinhlpg/vixtts-demo)
+
+### Usage
+
+For a quick usage, please checkout [this notebook](https://colab.research.google.com/drive/1q9vA7mDyvK_u0ijDDNuycDoUUbryM3p3?usp=sharing)
+
+### License
+
+This model is licensed under [Coqui Public Model License](https://coqui.ai/cpml).
+
+### Contact
+
+Fine-tuned by Thinh Le at FPT University HCMC, as a component of [Non La](https://huggingface.co/capleaf)'s graduation thesis.
+Contact:
+
+- You can message me directly on Facebook: <https://fb.com/thinhlpg/> (preferred 🤗)
+- GitHub: <https://github.com/thinhlpg>
+- Email: <thinhlpg@gmail.com> or <thinhlpgse161384@fpt.edu.vn>

config.json

@@ -0,0 +1,176 @@
+{
+    "output_path": "output",
+    "logger_uri": null,
+    "run_name": "run",
+    "project_name": null,
+    "run_description": "viXTTS training",
+    "print_step": null,
+    "plot_step": null,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "save_on_interrupt": true,
+    "log_model_step": null,
+    "save_step": 24000,
+    "save_n_checkpoints": 2,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 0,
+    "target_loss": null,
+    "print_eval": true,
+    "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": 5,
+    "batch_size": 2,
+    "eval_batch_size": 2,
+    "grad_clip": 0.0,
+    "scheduler_after_epoch": true,
+    "lr": 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": 1,
+    "model": "xtts",
+    "num_loader_workers": 0,
+    "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": 48,
+    "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": 7544,
+        "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",
+        "vi"
+    ],
+    "temperature": 0.85,
+    "length_penalty": 1.0,
+    "repetition_penalty": 2.0,
+    "top_k": 50,
+    "top_p": 0.85,
+    "num_gpt_outputs": 1,
+    "gpt_cond_len": 12,
+    "gpt_cond_chunk_len": 4,
+    "max_ref_len": 10,
+    "sound_norm_refs": false
+}

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:534670e4b752002b7d7224e6ea1f467bd608c8dd3c36efaa45e1f4696e8bd1d2
+size 1875343894

samples/nam-calm.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274758c6b991f29e53261aa98bb9a7d5aad37c8a8776968845982e750681e00c
+size 744014

samples/nam-cham.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586be2752c4de191f094cd786a49ae7f14d7d8b8d5c9df8ea0ed8e385fd9f8ec
+size 783950

samples/nam-nhanh.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6dbf341ed3309f79a718a9beea59d4f3a5004ba4b6675dbb6382f41abf7ed5
+size 646222

samples/nam-truyen-cam.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9e430ec2e6d78a8f282126923f19ae45c12c937c77a5b023dc501954fc4fa4
+size 875598

samples/nu-calm.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a023eb447f851673cc9a9f61ca9b99263724d31d057004eb37b84925c9b5bc6
+size 759374

samples/nu-cham.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acee1c4cc033c27fd78a0bd4f7041d78db59abf1b075ce3e5d4141bb35ef1508
+size 933454

samples/nu-luu-loat.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a120871b168489a33b7f3188764b0f973583bf5284bd96cd805d9e6256a7e45
+size 710734

samples/nu-nhan-nha.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c039491a0d5e44be9bd24222277d39dc3db1cecb6e6f9270fcc99a997837dd0
+size 763982

samples/nu-nhe-nhang.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6a0e132a37aa6d28a610eed3daa151309c4a98453d1da1d94d9e88c8438f8c
+size 793166

user_sample.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d8d594013b1fdd3c6b8c1d095735510899cd0d56bd2003f8367b6aced2e094
+size 5670316

vi_sample.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6a0e132a37aa6d28a610eed3daa151309c4a98453d1da1d94d9e88c8438f8c
+size 793166