Updates

README.md

@@ -1,33 +1,55 @@
 ---
-title: TensorFlowTTS
-emoji: 💩
-colorFrom: green
-colorTo: indigo
-sdk: gradio
-app_file: app.py
-pinned: false
+tags:
+- TensorFlowTTS
+- audio
+- text-to-speech
+- text-to-mel
+language: eng
+license: apache-2.0
+datasets:
+- LJSpeech
+widget:
+- text: "How are you?"
 ---
 
-# Configuration
 
-`title`: _string_  
-Display title for the Space
 
-`emoji`: _string_  
-Space emoji (emoji-only character allowed)
+This repository provides a pretrained [FastSpeech](https://arxiv.org/abs/1905.09263) trained on LJSpeech dataset (ENG). For a detail of the model, we encourage you to read more about
+[TensorFlowTTS](https://github.com/TensorSpeech/TensorFlowTTS). 
+
+
+## Install TensorFlowTTS
+First of all, please install TensorFlowTTS with the following command:
+```
+pip install TensorFlowTTS
+```
+
+### Converting your Text to Mel Spectrogram
+```python
+import numpy as np
+import soundfile as sf
+import yaml
+
+import tensorflow as tf
+
+from tensorflow_tts.inference import AutoProcessor
+from tensorflow_tts.inference import TFAutoModel
+
+processor = AutoProcessor.from_pretrained("ruslanmv/tts-fastspeech-ljspeech-en")
+fastspeech = TFAutoModel.from_pretrained("ruslanmv/tts-fastspeech-ljspeech-en")
+
+text = "How are you?"
+
+input_ids = processor.text_to_sequence(text)
+
+mel_before, mel_after, duration_outputs = fastspeech.inference(
+    input_ids=tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0),
+    speaker_ids=tf.convert_to_tensor([0], dtype=tf.int32),
+    speed_ratios=tf.convert_to_tensor([1.0], dtype=tf.float32),
+)
+```
 
-`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` or `streamlit`
 
-`app_file`: _string_  
-Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
-Path is relative to the root of the repository.
 
-`pinned`: _boolean_  
-Whether the Space stays on top of your list.

app.py

@@ -1,56 +0,0 @@
-import numpy as np
-import soundfile as sf
-import yaml
-
-import tensorflow as tf
-
-from tensorflow_tts.inference import TFAutoModel
-from tensorflow_tts.inference import AutoProcessor
-import gradio as gr
-
-# initialize fastspeech2 model.
-fastspeech2 = TFAutoModel.from_pretrained("tensorspeech/tts-fastspeech2-ljspeech-en")
-
-
-# initialize mb_melgan model
-mb_melgan = TFAutoModel.from_pretrained("tensorspeech/tts-mb_melgan-ljspeech-en")
-
-
-# inference
-processor = AutoProcessor.from_pretrained("tensorspeech/tts-fastspeech2-ljspeech-en")
-
-def inference(text):
-  input_ids = processor.text_to_sequence(text)
-  # fastspeech inference
-  
-  mel_before, mel_after, duration_outputs, _, _ = fastspeech2.inference(
-      input_ids=tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0),
-      speaker_ids=tf.convert_to_tensor([0], dtype=tf.int32),
-      speed_ratios=tf.convert_to_tensor([1.0], dtype=tf.float32),
-      f0_ratios =tf.convert_to_tensor([1.0], dtype=tf.float32),
-      energy_ratios =tf.convert_to_tensor([1.0], dtype=tf.float32),
-  )
-  
-  # melgan inference
-  audio_before = mb_melgan.inference(mel_before)[0, :, 0]
-  audio_after = mb_melgan.inference(mel_after)[0, :, 0]
-  
-  # save to file
-  sf.write('./audio_before.wav', audio_before, 22050, "PCM_16")
-  sf.write('./audio_after.wav', audio_after, 22050, "PCM_16")
-  return './audio_after.wav'
-  
-inputs = gr.inputs.Textbox(lines=5, label="Input Text")
-outputs =  gr.outputs.Audio(type="file", label="Output Audio")
-
-
-title = "Tensorflow TTS"
-description = "Gradio demo for TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2. To use it, simply add your text, or click one of the examples to load them. Read more at the links below."
-article = "<p style='text-align: center'><a href='https://tensorspeech.github.io/TensorFlowTTS/'>TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2</a> | <a href='https://github.com/TensorSpeech/TensorFlowTTS'>Github Repo</a></p>"
-
-examples = [
- ["TensorFlowTTS provides real-time state-of-the-art speech synthesis architectures such as Tacotron-2, Melgan, Multiband-Melgan, FastSpeech, FastSpeech2 based-on TensorFlow 2."],
- ["With Tensorflow 2, we can speed-up training/inference progress, optimizer further by using fake-quantize aware and pruning, make TTS models can be run faster than real-time and be able to deploy on mobile devices or embedded systems."]   
-]
-
-gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, examples=examples).launch()

config.yml

@@ -0,0 +1,79 @@
+# This is the hyperparameter configuration file for FastSpeech v3.
+# Please make sure this is adjusted for the LJSpeech dataset. If you want to
+# apply to the other dataset, you might need to carefully change some parameters.
+# This configuration performs 200k iters but a best checkpoint is around 150k iters.
+
+###########################################################
+#                FEATURE EXTRACTION SETTING               #
+###########################################################
+hop_size: 256            # Hop size.
+format: "npy"
+
+
+###########################################################
+#              NETWORK ARCHITECTURE SETTING               #
+###########################################################
+model_type: "fastspeech"
+
+fastspeech_params:
+    n_speakers: 1
+    encoder_hidden_size: 384
+    encoder_num_hidden_layers: 4
+    encoder_num_attention_heads: 2
+    encoder_attention_head_size: 192  # hidden_size // num_attention_heads
+    encoder_intermediate_size: 1024
+    encoder_intermediate_kernel_size: 3
+    encoder_hidden_act: "mish"
+    decoder_hidden_size: 384
+    decoder_num_hidden_layers: 4
+    decoder_num_attention_heads: 2
+    decoder_attention_head_size: 192  # hidden_size // num_attention_heads
+    decoder_intermediate_size: 1024
+    decoder_intermediate_kernel_size: 3
+    decoder_hidden_act: "mish"
+    num_duration_conv_layers: 2
+    duration_predictor_filters: 256
+    duration_predictor_kernel_sizes: 3
+    num_mels: 80
+    hidden_dropout_prob: 0.2
+    attention_probs_dropout_prob: 0.1
+    duration_predictor_dropout_probs: 0.2
+    max_position_embeddings: 2048
+    initializer_range: 0.02
+    output_attentions: False
+    output_hidden_states: False
+
+###########################################################
+#                  DATA LOADER SETTING                    #
+###########################################################
+batch_size: 16              # Batch size for each GPU with assuming that gradient_accumulation_steps == 1.
+remove_short_samples: true  # Whether to remove samples the length of which are less than batch_max_steps.
+allow_cache: true           # Whether to allow cache in dataset. If true, it requires cpu memory.
+mel_length_threshold: 32    # remove all targets has mel_length <= 32 
+is_shuffle: true            # shuffle dataset after each epoch.
+###########################################################
+#             OPTIMIZER & SCHEDULER SETTING               #
+###########################################################
+optimizer_params:
+    initial_learning_rate: 0.001
+    end_learning_rate: 0.00005
+    decay_steps: 150000          # < train_max_steps is recommend.
+    warmup_proportion: 0.02
+    weight_decay: 0.001
+
+gradient_accumulation_steps: 1
+var_train_expr: null  # trainable variable expr (eg. 'embeddings|encoder|decoder' )
+                      # must separate by |. if var_train_expr is null then we 
+                      # training all variable     
+###########################################################
+#                    INTERVAL SETTING                     #
+###########################################################
+train_max_steps: 200000               # Number of training steps.
+save_interval_steps: 5000             # Interval steps to save checkpoint.
+eval_interval_steps: 500              # Interval steps to evaluate the network.
+log_interval_steps: 200               # Interval steps to record the training log.
+
+###########################################################
+#                     OTHER SETTING                       #
+###########################################################
+num_save_intermediate_results: 1  # Number of batch to be saved as intermediate results.

model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d0352241536eec6bb426dfa8d69b8a5a96bb6ef51fe3a5599b68ec190b83a85
+size 120784120

packages.txt

@@ -1 +0,0 @@
-libsndfile1

processor.json

@@ -0,0 +1 @@
+{"symbol_to_id": {"pad": 0, "-": 1, "!": 2, "'": 3, "(": 4, ")": 5, ",": 6, ".": 7, ":": 8, ";": 9, "?": 10, " ": 11, "A": 12, "B": 13, "C": 14, "D": 15, "E": 16, "F": 17, "G": 18, "H": 19, "I": 20, "J": 21, "K": 22, "L": 23, "M": 24, "N": 25, "O": 26, "P": 27, "Q": 28, "R": 29, "S": 30, "T": 31, "U": 32, "V": 33, "W": 34, "X": 35, "Y": 36, "Z": 37, "a": 38, "b": 39, "c": 40, "d": 41, "e": 42, "f": 43, "g": 44, "h": 45, "i": 46, "j": 47, "k": 48, "l": 49, "m": 50, "n": 51, "o": 52, "p": 53, "q": 54, "r": 55, "s": 56, "t": 57, "u": 58, "v": 59, "w": 60, "x": 61, "y": 62, "z": 63, "@AA": 64, "@AA0": 65, "@AA1": 66, "@AA2": 67, "@AE": 68, "@AE0": 69, "@AE1": 70, "@AE2": 71, "@AH": 72, "@AH0": 73, "@AH1": 74, "@AH2": 75, "@AO": 76, "@AO0": 77, "@AO1": 78, "@AO2": 79, "@AW": 80, "@AW0": 81, "@AW1": 82, "@AW2": 83, "@AY": 84, "@AY0": 85, "@AY1": 86, "@AY2": 87, "@B": 88, "@CH": 89, "@D": 90, "@DH": 91, "@EH": 92, "@EH0": 93, "@EH1": 94, "@EH2": 95, "@ER": 96, "@ER0": 97, "@ER1": 98, "@ER2": 99, "@EY": 100, "@EY0": 101, "@EY1": 102, "@EY2": 103, "@F": 104, "@G": 105, "@HH": 106, "@IH": 107, "@IH0": 108, "@IH1": 109, "@IH2": 110, "@IY": 111, "@IY0": 112, "@IY1": 113, "@IY2": 114, "@JH": 115, "@K": 116, "@L": 117, "@M": 118, "@N": 119, "@NG": 120, "@OW": 121, "@OW0": 122, "@OW1": 123, "@OW2": 124, "@OY": 125, "@OY0": 126, "@OY1": 127, "@OY2": 128, "@P": 129, "@R": 130, "@S": 131, "@SH": 132, "@T": 133, "@TH": 134, "@UH": 135, "@UH0": 136, "@UH1": 137, "@UH2": 138, "@UW": 139, "@UW0": 140, "@UW1": 141, "@UW2": 142, "@V": 143, "@W": 144, "@Y": 145, "@Z": 146, "@ZH": 147, "eos": 148}, "id_to_symbol": {"0": "pad", "1": "-", "2": "!", "3": "'", "4": "(", "5": ")", "6": ",", "7": ".", "8": ":", "9": ";", "10": "?", "11": " ", "12": "A", "13": "B", "14": "C", "15": "D", "16": "E", "17": "F", "18": "G", "19": "H", "20": "I", "21": "J", "22": "K", "23": "L", "24": "M", "25": "N", "26": "O", "27": "P", "28": "Q", "29": "R", "30": "S", "31": "T", "32": "U", "33": "V", "34": "W", "35": "X", "36": "Y", "37": "Z", "38": "a", "39": "b", "40": "c", "41": "d", "42": "e", "43": "f", "44": "g", "45": "h", "46": "i", "47": "j", "48": "k", "49": "l", "50": "m", "51": "n", "52": "o", "53": "p", "54": "q", "55": "r", "56": "s", "57": "t", "58": "u", "59": "v", "60": "w", "61": "x", "62": "y", "63": "z", "64": "@AA", "65": "@AA0", "66": "@AA1", "67": "@AA2", "68": "@AE", "69": "@AE0", "70": "@AE1", "71": "@AE2", "72": "@AH", "73": "@AH0", "74": "@AH1", "75": "@AH2", "76": "@AO", "77": "@AO0", "78": "@AO1", "79": "@AO2", "80": "@AW", "81": "@AW0", "82": "@AW1", "83": "@AW2", "84": "@AY", "85": "@AY0", "86": "@AY1", "87": "@AY2", "88": "@B", "89": "@CH", "90": "@D", "91": "@DH", "92": "@EH", "93": "@EH0", "94": "@EH1", "95": "@EH2", "96": "@ER", "97": "@ER0", "98": "@ER1", "99": "@ER2", "100": "@EY", "101": "@EY0", "102": "@EY1", "103": "@EY2", "104": "@F", "105": "@G", "106": "@HH", "107": "@IH", "108": "@IH0", "109": "@IH1", "110": "@IH2", "111": "@IY", "112": "@IY0", "113": "@IY1", "114": "@IY2", "115": "@JH", "116": "@K", "117": "@L", "118": "@M", "119": "@N", "120": "@NG", "121": "@OW", "122": "@OW0", "123": "@OW1", "124": "@OW2", "125": "@OY", "126": "@OY0", "127": "@OY1", "128": "@OY2", "129": "@P", "130": "@R", "131": "@S", "132": "@SH", "133": "@T", "134": "@TH", "135": "@UH", "136": "@UH0", "137": "@UH1", "138": "@UH2", "139": "@UW", "140": "@UW0", "141": "@UW1", "142": "@UW2", "143": "@V", "144": "@W", "145": "@Y", "146": "@Z", "147": "@ZH", "148": "eos"}, "speakers_map": {"ljspeech": 0}, "processor_name": "LJSpeechProcessor"}

requirements.txt

@@ -1,5 +0,0 @@
-TensorFlowTTS
-gradio 
-numpy
-SoundFile
-git+https://github.com/repodiac/german_transliterate