import & fix

README.md

@@ -1,12 +1,30 @@
 ---
-title: Coqui Tts Cat
-emoji: 📉
-colorFrom: yellow
-colorTo: pink
+title: BSC VITS
+emoji: 🗣️
+colorFrom: blue
+colorTo: white
 sdk: gradio
-sdk_version: 3.28.0
 app_file: app.py
 pinned: false
 ---
+# Configuration
+`title`: _string_
+Display title for the Space
+`emoji`: _string_
+Space emoji (emoji-only character allowed)
+`colorFrom`: _string_
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+`colorTo`: _string_
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+`sdk`: _string_
+Can be either `gradio`, `streamlit`, or `static`
+`sdk_version` : _string_
+Only applicable for `streamlit` SDK.
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+`app_file`: _string_
+Path to your main application file (which contains either `gradio` or `streamlit` Python code, or `static` html code).
+Path is relative to the root of the repository.
+
+`pinned`: _boolean_
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,77 @@
+import tempfile
+from typing import Optional
+from TTS.config import load_config
+import gradio as gr
+import numpy as np
+import os
+import json
+from TTS.utils.manage import ModelManager
+from TTS.utils.synthesizer import Synthesizer
+
+
+MAX_TXT_LEN = 100
+
+SPEAKERS = ['f_cen_05', 'f_cen_81', 'f_occ_31', 'f_occ_de', 'f_sep_31', 'm_cen_08', 'm_occ_44', 'm_val_89']
+
+def tts(text: str, speaker_idx: str=None):
+    if len(text) > MAX_TXT_LEN:
+        text = text[:MAX_TXT_LEN]
+        print(f"Input text was cutoff since it went over the {MAX_TXT_LEN} character limit.")
+    print(text)
+
+    model_path = os.getcwd() + "/best_model.pth"
+    config_path = os.getcwd() + "/config.json"
+    speakers_file_path = os.getcwd() + "/speakers.pth"
+    speakers_maping_path = os.getcwd() + "/speaker_map.json"
+    vocoder_path = None
+    vocoder_config_path = None
+
+    synthesizer = Synthesizer(
+        model_path, config_path, speakers_file_path, None, vocoder_path, vocoder_config_path,
+    )
+
+    # Map speaker aliases to speaker ids
+    with open(speakers_maping_path, 'r') as fp:
+        maping = json.load(fp)
+
+    speaker_idx = maping[speaker_idx]
+
+    # synthesize
+    if synthesizer is None:
+        raise NameError("model not found")
+    wavs = synthesizer.tts(text, speaker_idx)
+    # return output
+    with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as fp:
+        synthesizer.save_wav(wavs, fp)
+        return fp.name
+
+
+description="""
+1️⃣ Introdueix el text a sintetitzar.
+
+2️⃣ Selecciona una veu en el desplegable.
+
+3️⃣ Gaudeix!
+"""
+article= ""
+
+iface = gr.Interface(
+    fn=tts,
+    inputs=[
+        gr.inputs.Textbox(
+            label="Text",
+            default="Introdueix el text a sintetitzar.",
+        ),
+        gr.inputs.Dropdown(label="Selecciona un parlant", choices=SPEAKERS, default=None)
+    ],
+    outputs=gr.outputs.Audio(label="Output",type="filepath"),
+    title="🗣️ TTS Català Multi Parlant - VITS 🗣️",
+    theme="grass",
+    description=description,
+    article=article,
+    allow_flagging=False,
+    flagging_options=['error', 'bad-quality', 'wrong-pronounciation'],
+    layout="vertical",
+    live=False
+)
+iface.launch(share=False)

best_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15fa7d2052bada1cf421e49d2d03b00e95b49fcd0e42b7af1d92da2880cdecc
+size 1038659133

config.json

@@ -0,0 +1,262 @@
+{
+    "output_path": "/gpfs/projects/bsc88/speech/tts/TTS_v0.8.0/recipes/multispeaker/experiments_from_previous",
+    "logger_uri": null,
+    "run_name": "multispeaker_vits_ca_1e4_1e4_32",
+    "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",
+    "log_model_step": 1000,
+    "save_step": 1000,
+    "save_n_checkpoints": 5,
+    "save_checkpoints": true,
+    "save_all_best": true,
+    "save_best_after": 10000,
+    "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": false,
+    "epochs": 1000,
+    "batch_size": 16,
+    "eval_batch_size": 8,
+    "grad_clip": [
+        1000.0,
+        1000.0
+    ],
+    "scheduler_after_epoch": true,
+    "lr": 0.001,
+    "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,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "vits",
+    "num_loader_workers": 4,
+    "num_eval_loader_workers": 4,
+    "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": true,
+    "phonemizer": "espeak",
+    "phoneme_language": "ca",
+    "compute_input_seq_cache": true,
+    "text_cleaner": "multilingual_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/gpfs/projects/bsc88/speech/tts/TTS_v0.8.0/recipes/multispeaker/phoneme_cache",
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.IPAPhonemes",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "iy\u0268\u0289\u026fu\u026a\u028f\u028ae\u00f8\u0258\u0259\u0275\u0264o\u025b\u0153\u025c\u025e\u028c\u0254\u00e6\u0250a\u0276\u0251\u0252\u1d7b\u0298\u0253\u01c0\u0257\u01c3\u0284\u01c2\u0260\u01c1\u029bpbtd\u0288\u0256c\u025fk\u0261q\u0262\u0294\u0274\u014b\u0272\u0273n\u0271m\u0299r\u0280\u2c71\u027e\u027d\u0278\u03b2fv\u03b8\u00f0sz\u0283\u0292\u0282\u0290\u00e7\u029dx\u0263\u03c7\u0281\u0127\u0295h\u0266\u026c\u026e\u028b\u0279\u027bj\u0270l\u026d\u028e\u029f\u02c8\u02cc\u02d0\u02d1\u028dw\u0265\u029c\u02a2\u02a1\u0255\u0291\u027a\u0267\u02b2\u025a\u02de\u026b",
+        "punctuations": "!'(),-.:;? ",
+        "phonemes": null,
+        "is_unique": false,
+        "is_sorted": true
+    },
+    "add_blank": true,
+    "batch_group_size": 5,
+    "loss_masking": null,
+    "min_audio_len": 1,
+    "max_audio_len": Infinity,
+    "min_text_len": 1,
+    "max_text_len": 325,
+    "compute_f0": false,
+    "compute_linear_spec": true,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "datasets": [
+        {
+            "formatter": "vctk_old",
+            "dataset_name": "vctk_old",
+            "path": "/gpfs/scratch/bsc88/bsc88474/data/multispeaker_ca",
+            "meta_file_train": "",
+            "ignored_speakers": [
+                "uri",
+                "09796",
+                "05450"
+            ],
+            "language": "ca",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "Per exemple, dels nostres bancs que inverteixen en armament de les nostres empreses."
+        ],
+        [
+            "Preguntin-se si aix\u00f2 era necessari."
+        ],
+        [
+            "La suposada ocultaci\u00f3 dels informes que advertien de risc s\u00edsmic."
+        ],
+        [
+            "\u00c9s de 633 milions d'euros quan es far\u00e0 la publicaci\u00f3 detallada."
+        ]
+    ],
+    "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": 131,
+        "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": true,
+        "num_speakers": 257,
+        "speakers_file": "/home/user/app/speakers.pth",
+        "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": 0.0001,
+    "lr_disc": 0.0001,
+    "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": 257,
+    "use_speaker_embedding": true,
+    "speakers_file": "/home/user/app/speakers.pth",
+    "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
+}

packages.txt

@@ -0,0 +1,2 @@
+libsndfile1
+espeak-ng

requirements.txt

@@ -0,0 +1 @@
+git+https://github.com/coqui-ai/TTS@dev#egg=TTS

speaker_map.json

@@ -0,0 +1,10 @@
+{
+    "f_cen_05": "05739",
+    "f_cen_81": "8162d651b6211f06f655a69cd7fdd383d6b4287e9ba132b9898ef9ac8687349e777626333d23bed93f9264aae965efb14ed650cb64fd0ad90494aff903eaef11",
+    "f_occ_31": "31535cb2ece4710d08fdbeefb6f8f75ed093fee4cf8573bd601d960f8c6156f0fd0a85712761691e86e31160b993ee0eacb10c4c8aed000cc394cf7c7d207a7e",
+    "f_occ_de": "dee065b956b99b10db4763759d64c41791af1a7e77f1864f90a2b0847a12633dcf9bc108db7eaf73cc8d0e750f5c37383a56cd77cc2276d3960104c6bebe6346",
+    "f_sep_31": "31e6f3a011661320b2e59b6f8be43f6db2243e9feabc2b9787c1413788e13eb0e5810bed983bf7ff66e46417d183a91ed50b3b9be9d89e4f51aada72293b9881",
+    "m_cen_08": "08935",
+    "m_occ_44": "30b1f81c579755895581259d79a8a5a3ca45b908b0bd14ad1c6418f39aa1e2f47cb4749c69b5440cdb92e3bafb772e19e7bc2b16d196b061addd173a1309e491",
+    "m_val_89": "896256329fbeb5b8116349c31d8a39a7d36d5f970d48558e1db5417d611e240e4dbf473f6e49137f7aa6116394b7deabb0bbec4a014896cdc9484ee91458117d"
+}

speakers.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dacda0b8dd3e111c5072f8f33c08b4a29b92ac79aaf22ceca912d01e7deb905
+size 30191