Upload best Bangla VITS TTS checkpoint

README.md

@@ -0,0 +1,42 @@
+---
+language:
+- bn
+license: apache-2.0
+tags:
+- text-to-speech
+- bangla
+- bengali
+- vits
+- coqui-tts
+- women-health
+pipeline_tag: text-to-speech
+---
+
+# MenoChat VITS Bangla TTS
+
+This is a Bangla VITS text-to-speech model fine-tuned for MenoChat-style women's health conversational responses.
+
+## Model Details
+
+- Architecture: VITS
+- Framework: Coqui TTS
+- Language: Bangla / Bengali
+- Sample rate: 22,050 Hz
+- Training setup: 50-epoch fine-tuning
+- Best checkpoint: `best_model.pth`, uploaded as `pytorch_model.pth`
+- Domain: menstrual and menopausal health support dialogue
+
+## Intended Use
+
+This model is intended for generating Bangla speech for a women’s health conversational assistant.
+
+
+## Files
+
+- `pytorch_model.pth`: best fine-tuned VITS checkpoint
+- `config.json`: model configuration
+- `training_info.json`: training metadata
+
+## Inference
+
+This model is intended to be loaded with Coqui TTS-compatible VITS inference code.

config.json

@@ -0,0 +1,270 @@
+{
+    "output_path": "/workspace/tts_runs/finetune_hf_vits_menochat_grapheme_keep_all_50ep",
+    "logger_uri": null,
+    "run_name": "finetune_hf_vits_menochat_grapheme_keep_all_50ep",
+    "project_name": "MenoChat_ViTs_Bangla_TTS",
+    "run_description": "50-epoch fine-tune of HF Bangla VITS checkpoint on full keep-all normalized MenoChat grapheme dataset.",
+    "print_step": 25,
+    "plot_step": 250,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "save_on_interrupt": true,
+    "log_model_step": null,
+    "save_step": 1000,
+    "save_n_checkpoints": 5,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 100,
+    "target_loss": null,
+    "print_eval": true,
+    "test_delay_epochs": -1,
+    "run_eval": true,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": true,
+    "precision": "fp16",
+    "epochs": 50,
+    "batch_size": 16,
+    "eval_batch_size": 8,
+    "grad_clip": [
+        1000.0,
+        1000.0
+    ],
+    "scheduler_after_epoch": true,
+    "lr": 5e-06,
+    "optimizer": "AdamW",
+    "optimizer_params": {
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "weight_decay": 0.01
+    },
+    "lr_scheduler": "",
+    "lr_scheduler_params": null,
+    "use_grad_scaler": false,
+    "allow_tf32": true,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 321,
+    "model": "vits",
+    "num_loader_workers": 6,
+    "num_eval_loader_workers": 3,
+    "use_noise_augment": false,
+    "audio": {
+        "fft_size": 1024,
+        "sample_rate": 22050,
+        "win_length": 1024,
+        "hop_length": 256,
+        "num_mels": 80,
+        "mel_fmin": 0,
+        "mel_fmax": null
+    },
+    "use_phonemes": false,
+    "phonemizer": null,
+    "phoneme_language": null,
+    "compute_input_seq_cache": true,
+    "text_cleaner": null,
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": null,
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.Graphemes",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "\u0964",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "\u0987\u0997\u0982\u09bc\u2019\u09c1\u0983\u09a8\u09e7\u099d\u09c2\u0993\u2018\u098a\u09cb\u099b\u09aa\u09ab\u09c8\u09ee\u09b7\u09af\u09ce\u09a2\u0988\u0995\u09a0\u09bf\u099c\u09e6\u09ec\u09c0\u099f\u09a1\u098f\u0985\u098b\u09a7\u099a\u09c7\u09e8\u09e9\u09a3\u0989\u09df\u09dd\u0996\u09b2\u09ad\u09d7\u09b8\u09b9\u09cd\u09dc\u09a6\u09a5\u09ac\u0994\u09be\u099e\u09b6\u09b0\u09cc\u09ae\u2014\u0990\u0986\u09c3\u0998\u0999\u200c\u0981\u09ea\u09eb\u09a4",
+        "punctuations": ".?-!|, ",
+        "phonemes": null,
+        "is_unique": true,
+        "is_sorted": true
+    },
+    "add_blank": true,
+    "batch_group_size": 0,
+    "loss_masking": null,
+    "min_audio_len": 1,
+    "max_audio_len": 286650,
+    "min_text_len": 1,
+    "max_text_len": 220,
+    "compute_f0": false,
+    "compute_energy": false,
+    "compute_linear_spec": true,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "shuffle": false,
+    "drop_last": false,
+    "datasets": [
+        {
+            "formatter": "menochat_ljspeech",
+            "dataset_name": "menochat_grapheme_keep_all",
+            "path": "/workspace/data_trainingv5/tts_v1_vits_22050_ljspeech_grapheme_keep_all",
+            "meta_file_train": "metadata_train.csv",
+            "ignored_speakers": null,
+            "language": "bn",
+            "phonemizer": "",
+            "meta_file_val": "metadata_val.csv",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "\u0986\u09aa\u09c1, \u0986\u09aa\u09a8\u09be\u09b0 \u0995\u09b7\u09cd\u099f\u099f\u09be \u0986\u09ae\u09bf \u09ac\u09c1\u099d\u09a4\u09c7 \u09aa\u09be\u09b0\u099b\u09bf."
+        ],
+        [
+            "\u09ae\u09be\u09b8\u09bf\u0995\u09c7\u09b0 \u09b8\u09ae\u09af\u09bc \u09b6\u09b0\u09c0\u09b0\u09c7\u09b0 \u09af\u09a4\u09cd\u09a8 \u09a8\u09c7\u0993\u09af\u09bc\u09be \u0996\u09c1\u09ac \u099c\u09b0\u09c1\u09b0\u09bf."
+        ],
+        [
+            "\u09b9\u09b0\u09ae\u09cb\u09a8 \u09b0\u09bf\u09aa\u09cd\u09b2\u09c7\u09b8\u09ae\u09c7\u09a8\u09cd\u099f \u09a5\u09c7\u09b0\u09be\u09aa\u09bf \u0995\u09bf \u09a8\u09bf\u09b0\u09be\u09aa\u09a6?"
+        ],
+        [
+            "\u09aa\u09b2\u09bf\u09b8\u09bf\u09b8\u09cd\u099f\u09bf\u0995 \u0993\u09ad\u09be\u09b0\u09bf \u09b8\u09bf\u09a8\u09cd\u09a1\u09cd\u09b0\u09cb\u09ae \u09a5\u09be\u0995\u09b2\u09c7 \u09aa\u09bf\u09b0\u09bf\u09af\u09bc\u09a1 \u0985\u09a8\u09bf\u09af\u09bc\u09ae\u09bf\u09a4 \u09b9\u09a4\u09c7 \u09aa\u09be\u09b0\u09c7."
+        ],
+        [
+            "\u09b9\u099f \u09ab\u09cd\u09b2\u09cd\u09af\u09be\u09b6 \u09b9\u09b2\u09c7 \u0998\u09c1\u09ae \u09ad\u09c7\u0999\u09c7 \u09af\u09c7\u09a4\u09c7 \u09aa\u09be\u09b0\u09c7."
+        ]
+    ],
+    "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": {
+        "num_chars": 86,
+        "out_channels": 513,
+        "spec_segment_size": 32,
+        "hidden_channels": 192,
+        "hidden_channels_ffn_text_encoder": 768,
+        "num_heads_text_encoder": 2,
+        "num_layers_text_encoder": 6,
+        "kernel_size_text_encoder": 3,
+        "dropout_p_text_encoder": 0.1,
+        "dropout_p_duration_predictor": 0.5,
+        "kernel_size_posterior_encoder": 5,
+        "dilation_rate_posterior_encoder": 1,
+        "num_layers_posterior_encoder": 16,
+        "kernel_size_flow": 5,
+        "dilation_rate_flow": 1,
+        "num_layers_flow": 4,
+        "resblock_type_decoder": "1",
+        "resblock_kernel_sizes_decoder": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes_decoder": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates_decoder": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel_decoder": 512,
+        "upsample_kernel_sizes_decoder": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "periods_multi_period_discriminator": [
+            2,
+            3,
+            5,
+            7,
+            11
+        ],
+        "use_sdp": true,
+        "noise_scale": 1.0,
+        "inference_noise_scale": 0.667,
+        "length_scale": 1.0,
+        "noise_scale_dp": 1.0,
+        "inference_noise_scale_dp": 1.0,
+        "max_inference_len": null,
+        "init_discriminator": true,
+        "use_spectral_norm_disriminator": false,
+        "use_speaker_embedding": false,
+        "num_speakers": 0,
+        "speakers_file": null,
+        "d_vector_file": null,
+        "speaker_embedding_channels": 256,
+        "use_d_vector_file": false,
+        "d_vector_dim": 0,
+        "detach_dp_input": true,
+        "use_language_embedding": false,
+        "embedded_language_dim": 4,
+        "num_languages": 0,
+        "language_ids_file": null,
+        "use_speaker_encoder_as_loss": false,
+        "speaker_encoder_config_path": "",
+        "speaker_encoder_model_path": "",
+        "condition_dp_on_speaker": true,
+        "freeze_encoder": false,
+        "freeze_DP": false,
+        "freeze_PE": false,
+        "freeze_flow_decoder": false,
+        "freeze_waveform_decoder": false,
+        "encoder_sample_rate": null,
+        "interpolate_z": true,
+        "reinit_DP": false,
+        "reinit_text_encoder": false
+    },
+    "lr_gen": 5e-06,
+    "lr_disc": 5e-06,
+    "lr_scheduler_gen": "ExponentialLR",
+    "lr_scheduler_gen_params": {
+        "gamma": 0.999875,
+        "last_epoch": -1
+    },
+    "lr_scheduler_disc": "ExponentialLR",
+    "lr_scheduler_disc_params": {
+        "gamma": 0.999875,
+        "last_epoch": -1
+    },
+    "kl_loss_alpha": 1.0,
+    "disc_loss_alpha": 1.0,
+    "gen_loss_alpha": 1.0,
+    "feat_loss_alpha": 1.0,
+    "mel_loss_alpha": 45.0,
+    "dur_loss_alpha": 1.0,
+    "speaker_encoder_loss_alpha": 1.0,
+    "return_wav": true,
+    "use_weighted_sampler": false,
+    "weighted_sampler_attrs": null,
+    "weighted_sampler_multipliers": null,
+    "r": 1,
+    "num_speakers": 0,
+    "use_speaker_embedding": false,
+    "speakers_file": null,
+    "speaker_embedding_channels": 256,
+    "language_ids_file": null,
+    "use_language_embedding": false,
+    "use_d_vector_file": false,
+    "d_vector_file": null,
+    "d_vector_dim": 0,
+    "restore_path": "/workspace/hf_models/MenoChat_ViTs_Bangla_TTS/pytorch_model.pth",
+    "github_branch": "inside_docker"
+}

pytorch_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b473d31fd06eaa0f0babf27f285a79a8df542427d66fe73896268142c617fd2c
+size 997818614

training_info.json

@@ -0,0 +1,13 @@
+{
+  "model_type": "Coqui TTS VITS",
+  "language": "Bangla/Bengali",
+  "task": "text-to-speech",
+  "checkpoint_name": "best_model.pth",
+  "checkpoint_source": "/workspace/tts_runs/finetune_hf_vits_menochat_grapheme_keep_all_50ep/finetune_hf_vits_menochat_grapheme_keep_all_50ep-June-06-2026_07+00PM-0000000/best_model.pth",
+  "training_run_folder": "/workspace/tts_runs/finetune_hf_vits_menochat_grapheme_keep_all_50ep/finetune_hf_vits_menochat_grapheme_keep_all_50ep-June-06-2026_07+00PM-0000000",
+  "config_source": "/workspace/tts_runs/finetune_hf_vits_menochat_grapheme_keep_all_50ep/finetune_hf_vits_menochat_grapheme_keep_all_50ep-June-06-2026_07+00PM-0000000/config.json",
+  "epochs": 50,
+  "sample_rate": 22050,
+  "checkpoint_size_mb": 951.59,
+  "notes": " MenoChat Bangla VITS TTS fine-tuning run."
+}