Merge pull request #4 from ylacombe/main

Update 300M reference to Mini or 600M

README.md

@@ -7,7 +7,7 @@ Contrarily to other TTS models, Parler-TTS is a **fully open-source** release. A
 This repository contains the inference and training code for Parler-TTS. It is designed to accompany the [Data-Speech](https://github.com/huggingface/dataspeech) repository for dataset annotation.
 
 > [!IMPORTANT]
-> We're proud to release Parler-TTS v0.1, our first 300M parameter model, trained on 10.5K hours of audio data.
+> We're proud to release [Parler-TTS Mini v0.1](https://huggingface.co/parler-tts/parler_tts_mini_v0.1), our first 600M parameter model, trained on 10.5K hours of audio data.
 > In the coming weeks, we'll be working on scaling up to 50k hours of data, in preparation for the v1 model.
 
 ## 📖 Quick Index
@@ -33,8 +33,8 @@ import torch
 
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 
-model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler_tts_300M_v0.1").to(device)
-tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler_tts_300M_v0.1")
+model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler_tts_mini_v0.1").to(device)
+tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler_tts_mini_v0.1")
 
 prompt = "Hey, how are you doing today?"
 description = "A female speaker with a slightly low-pitched voice delivers her words quite expressively, in a very confined sounding environment with clear audio quality. She speaks very fast."
@@ -63,7 +63,7 @@ The [training folder](/training/) contains all the information to train or fine-
 - [3. A training guide](/training/README.md#3-training)
 
 > [!IMPORTANT]
-> **TL;DR:** After having followed the [installation steps](/training/README.md#requirements), you can reproduce the Parler-TTS v0.1 training recipe with the following command line:
+> **TL;DR:** After having followed the [installation steps](/training/README.md#requirements), you can reproduce the Parler-TTS Mini v0.1 training recipe with the following command line:
 
 ```sh
 accelerate launch ./training/run_parler_tts_training.py ./helpers/training_configs/starting_point_0.01.json

helpers/gradio_demo/app.py

@@ -6,7 +6,7 @@ from transformers import AutoTokenizer, AutoFeatureExtractor, set_seed
 
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 
-repo_id = "parler-tts/parler_tts_300M_v0.1"
+repo_id = "parler-tts/parler_tts_mini_v0.1"
 
 model = ParlerTTSForConditionalGeneration.from_pretrained(repo_id).to(device)
 tokenizer = AutoTokenizer.from_pretrained(repo_id)

helpers/model_init_scripts/init_model_300M.py → helpers/model_init_scripts/init_model_600M.py

@@ -64,4 +64,4 @@ if __name__ == "__main__":
     model.config.pad_token_id = encodec_vocab_size
     model.config.decoder_start_token_id = encodec_vocab_size+1
 
-    model.save_pretrained(os.path.join(args.save_directory, "parler-tts-untrained-300M/"))
+    model.save_pretrained(os.path.join(args.save_directory, "parler-tts-untrained-600M/"))

helpers/push_to_hub_scripts/push_trained_parler_tts_to_hub.py

@@ -2,7 +2,7 @@ from parler_tts import ParlerTTSForConditionalGeneration
 from transformers import AutoTokenizer, AutoFeatureExtractor
 
 path = "TODO"
-repo_id = "parler_tts_300M"
+repo_id = "parler_tts_600M"
 
 
 AutoFeatureExtractor.from_pretrained("ylacombe/dac_44khZ_8kbps").push_to_hub(repo_id)

helpers/training_configs/librispeech_tts_r_300M_dummy.json

 {
-    "model_name_or_path": "./parler-tts-untrained-300M/parler-tts-untrained-300M/",
+    "model_name_or_path": "./parler-tts-untrained-600M/parler-tts-untrained-600M/",
     "save_to_disk":  "./tmp_dataset_audio/",
     "temporary_save_to_disk": "./audio_code_tmp/",
 

helpers/training_configs/starting_point_0.01.json

 {
-    "model_name_or_path": "./parler-tts-untrained-300M/parler-tts-untrained-300M/",
+    "model_name_or_path": "./parler-tts-untrained-600M/parler-tts-untrained-600M/",
     "save_to_disk":  "./tmp_dataset_audio/",
     "temporary_save_to_disk": "./audio_code_tmp/",
 

training/README.md

 # Training Parler-TTS
 
-**TL;DR:** After having followed the [installation steps](#requirements), you can reproduce the Parler-TTS v0.1 training recipe with the following command line:
+**TL;DR:** After having followed the [installation steps](#requirements), you can reproduce the [Parler-TTS Mini v0.1](https://huggingface.co/parler-tts/parler_tts_mini_v0.1) training recipe with the following command line:
 
 ```sh
 accelerate launch ./training/run_parler_tts_training.py ./helpers/training_configs/starting_point_0.01.json
@@ -71,7 +71,7 @@ And then enter an authentication token from https://huggingface.co/settings/toke
 
 Depending on your compute resources and your dataset, you need to choose between fine-tuning a pre-trained model and training a new model from scratch.
 
-In that sense, we released a 300M checkpoint trained on 10.5K hours of annotated data under the repository id: [`parler-tts/parler_tts_300M_v0.1`](https://huggingface.co/parler-tts/parler_tts_300M_v0.1), that you can fine-tune for your own use-case.
+In that sense, we released a 600M checkpoint trained on 10.5K hours of annotated data under the repository id: [`parler-tts/parler_tts_mini_v0.1`](https://huggingface.co/parler-tts/parler_tts_mini_v0.1), that you can fine-tune for your own use-case.
 
 You can also train you own model from scratch. You can find [here](/helpers/model_init_scripts/) examples on how to initialize a model from scratch. For example, you can initialize a dummy model with:
 
@@ -79,10 +79,10 @@ You can also train you own model from scratch. You can find [here](/helpers/mode
 python helpers/model_init_scripts/init_dummy_model.py ./parler-tts-untrained-dummy --text_model "google-t5/t5-small" --audio_model "parler-tts/dac_44khZ_8kbps"
 ```
 
-In the rest of this guide, and to reproduce the Parler-TTS v0.1 training recipe, we'll use a 300-M parameters that we'll initialize with:
+In the rest of this guide, and to reproduce the Parler-TTS Mini v0.1 training recipe, we'll use a 600M parameters model that we'll initialize with:
 
 ```sh
-python helpers/model_init_scripts/init_model_300M.py ./parler-tts-untrained-300M --text_model "google/flan-t5-base" --audio_model "parler-tts/dac_44khZ_8kbps"
+python helpers/model_init_scripts/init_model_600M.py ./parler-tts-untrained-600M --text_model "google/flan-t5-base" --audio_model "parler-tts/dac_44khZ_8kbps"
 ```
 
 
@@ -95,7 +95,7 @@ To train your own Parler-TTS, you need datasets with 3 main features:
 
 Note that we made the choice to use description of the main speech characteristics (speaker pitch, speaking rate, level of noise, etc.) but that you are free to use any handmade or generated text description that makes sense.
 
-To train Parler-TTS v0.1, we used:
+To train Parler-TTS Mini v0.1, we used:
 * The full [LibriTTS-R dataset](https://huggingface.co/datasets/blabble-io/libritts_r), a 1K hours high-quality speech dataset.
 * A [10K hours subset](https://huggingface.co/datasets/parler-tts/mls_eng_10k) of [Multilingual LibriSpeech](https://huggingface.co/datasets/facebook/multilingual_librispeech).
 
@@ -109,11 +109,11 @@ The script [`run_parler_tts_training.py`](/training/run_parler_tts_training.py)
 2. pre-compute audio tokens
 3. train Parler-TTS
 
-To train Parler-TTS v0.1, we roughly used:
+To train Parler-TTS Mini v0.1, we roughly used:
 
 ```sh
 accelerate launch ./training/run_parler_tts_training.py \
-    --model_name_or_path "./parler-tts-untrained-300M/parler-tts-untrained-300M/" \
+    --model_name_or_path "./parler-tts-untrained-600M/parler-tts-untrained-600M/" \
     --feature_extractor_name "parler-tts/dac_44khZ_8kbps" \
     --description_tokenizer_name "google/flan-t5-base" \
     --prompt_tokenizer_name "google/flan-t5-base" \
@@ -202,4 +202,4 @@ And finally, two additional comments:
 
 > [!TIP]
 > Fine-tuning is as easy as modifying `model_name_or_path` to a pre-trained model.
-> For example: `--model_name_or_path parler-tts/parler_tts_300M_v0.1`.
+> For example: `--model_name_or_path parler-tts/parler_tts_mini_v0.1`.