Updated configs

README.md

@@ -1,147 +0,0 @@
----
-library_name: transformers
-tags:
-- text-to-speech
-- annotation
-license: apache-2.0
-language:
-- en
-pipeline_tag: text-to-speech
-inference: false
-datasets:
-- parler-tts/mls_eng
-- parler-tts/libritts_r_filtered
-- parler-tts/libritts-r-filtered-speaker-descriptions
-- parler-tts/mls-eng-speaker-descriptions
----
-
-<img src="https://huggingface.co/datasets/parler-tts/images/resolve/main/thumbnail.png" alt="Parler Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
-
-
-# Parler-TTS Mini v1
-
-<a target="_blank" href="https://huggingface.co/spaces/parler-tts/parler_tts">
-  <img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-sm.svg" alt="Open in HuggingFace"/>
-</a>
-
-**Parler-TTS Mini v1** is a lightweight text-to-speech (TTS) model, trained on 45K hours of audio data, that can generate high-quality, natural sounding speech with features that can be controlled using a simple text prompt (e.g. gender, background noise, speaking rate, pitch and reverberation).
-
-With [Parler-TTS Large v1](https://huggingface.co/parler-tts/parler-tts-large-v1), this is the second set of models published as part of the [Parler-TTS](https://github.com/huggingface/parler-tts) project, which aims to provide the community with TTS training resources and dataset pre-processing code.
-
-## 📖 Quick Index
-* [👨‍💻 Installation](#👨‍💻-installation)
-* [🎲 Using a random voice](#🎲-random-voice)
-* [🎯 Using a specific speaker](#🎯-using-a-specific-speaker)
-* [Motivation](#motivation)
-* [Optimizing inference](https://github.com/huggingface/parler-tts/blob/main/INFERENCE.md)
-
-## 🛠️ Usage
-
-### 👨‍💻 Installation
-
-Using Parler-TTS is as simple as "bonjour". Simply install the library once:
-
-```sh
-pip install git+https://github.com/huggingface/parler-tts.git
-```
-
-### 🎲 Random voice
-
-
-**Parler-TTS** has been trained to generate speech with features that can be controlled with a simple text prompt, for example:
-
-```py
-import torch
-from parler_tts import ParlerTTSForConditionalGeneration
-from transformers import AutoTokenizer
-import soundfile as sf
-
-device = "cuda:0" if torch.cuda.is_available() else "cpu"
-
-model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler-tts-mini-v1").to(device)
-tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler-tts-mini-v1")
-
-prompt = "Hey, how are you doing today?"
-description = "A female speaker delivers a slightly expressive and animated speech with a moderate speed and pitch. The recording is of very high quality, with the speaker's voice sounding clear and very close up."
-
-input_ids = tokenizer(description, return_tensors="pt").input_ids.to(device)
-prompt_input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
-
-generation = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)
-audio_arr = generation.cpu().numpy().squeeze()
-sf.write("parler_tts_out.wav", audio_arr, model.config.sampling_rate)
-```
-
-### 🎯 Using a specific speaker
-
-To ensure speaker consistency across generations, this checkpoint was also trained on 34 speakers, characterized by name (e.g. Jon, Lea, Gary, Jenna, Mike, Laura).
-
-To take advantage of this, simply adapt your text description to specify which speaker to use: `Jon's voice is monotone yet slightly fast in delivery, with a very close recording that almost has no background noise.`
-
-```py
-import torch
-from parler_tts import ParlerTTSForConditionalGeneration
-from transformers import AutoTokenizer
-import soundfile as sf
-
-device = "cuda:0" if torch.cuda.is_available() else "cpu"
-
-model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler-tts-mini-v1").to(device)
-tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler-tts-mini-v1")
-
-prompt = "Hey, how are you doing today?"
-description = "Jon's voice is monotone yet slightly fast in delivery, with a very close recording that almost has no background noise."
-
-input_ids = tokenizer(description, return_tensors="pt").input_ids.to(device)
-prompt_input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
-
-generation = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)
-audio_arr = generation.cpu().numpy().squeeze()
-sf.write("parler_tts_out.wav", audio_arr, model.config.sampling_rate)
-```
-
-**Tips**:
-* We've set up an [inference guide](https://github.com/huggingface/parler-tts/blob/main/INFERENCE.md) to make generation faster. Think SDPA, torch.compile, batching and streaming!
-* Include the term "very clear audio" to generate the highest quality audio, and "very noisy audio" for high levels of background noise
-* Punctuation can be used to control the prosody of the generations, e.g. use commas to add small breaks in speech
-* The remaining speech features (gender, speaking rate, pitch and reverberation) can be controlled directly through the prompt
-
-## Motivation
-
-Parler-TTS is a reproduction of work from the paper [Natural language guidance of high-fidelity text-to-speech with synthetic annotations](https://www.text-description-to-speech.com) by Dan Lyth and Simon King, from Stability AI and Edinburgh University respectively. 
-
-Contrarily to other TTS models, Parler-TTS is a **fully open-source** release. All of the datasets, pre-processing, training code and weights are released publicly under permissive license, enabling the community to build on our work and develop their own powerful TTS models.
-Parler-TTS was released alongside:
-* [The Parler-TTS repository](https://github.com/huggingface/parler-tts) - you can train and fine-tuned your own version of the model.
-* [The Data-Speech repository](https://github.com/huggingface/dataspeech) - a suite of utility scripts designed to annotate speech datasets.
-* [The Parler-TTS organization](https://huggingface.co/parler-tts) - where you can find the annotated datasets as well as the future checkpoints.
-
-## Citation
-
-If you found this repository useful, please consider citing this work and also the original Stability AI paper:
-
-```
-@misc{lacombe-etal-2024-parler-tts,
-  author = {Yoach Lacombe and Vaibhav Srivastav and Sanchit Gandhi},
-  title = {Parler-TTS},
-  year = {2024},
-  publisher = {GitHub},
-  journal = {GitHub repository},
-  howpublished = {\url{https://github.com/huggingface/parler-tts}}
-}
-```
-
-```
-@misc{lyth2024natural,
-      title={Natural language guidance of high-fidelity text-to-speech with synthetic annotations},
-      author={Dan Lyth and Simon King},
-      year={2024},
-      eprint={2402.01912},
-      archivePrefix={arXiv},
-      primaryClass={cs.SD}
-}
-```
-
-## License
-
-This model is permissively licensed under the Apache 2.0 license.

config.json

@@ -1,9 +1,10 @@
 {
-  "_name_or_path": "/fsx/yoach/tmp/artefacts/training-50K-mini-without-accents-3-mononode/",
+  "_name_or_path": "speechmaster",
   "architectures": [
     "ParlerTTSForConditionalGeneration"
   ],
   "audio_encoder": {
+    "_attn_implementation_autoset": false,
     "_name_or_path": "parler-tts/dac_44khZ_8kbps",
     "add_cross_attention": false,
     "architectures": [
@@ -41,7 +42,7 @@
     "max_length": 20,
     "min_length": 0,
     "model_bitrate": 8,
-    "model_type": "dac",
+    "model_type": "dac_on_the_hub",
     "no_repeat_ngram_size": 0,
     "num_beam_groups": 1,
     "num_beams": 1,
@@ -75,6 +76,7 @@
     "use_bfloat16": false
   },
   "decoder": {
+    "_attn_implementation_autoset": false,
     "_name_or_path": "/fsx/yoach/tmp/artefacts/parler-tts-mini/decoder",
     "activation_dropout": 0.0,
     "activation_function": "gelu",
@@ -87,6 +89,7 @@
     "begin_suppress_tokens": null,
     "bos_token_id": 1025,
     "chunk_size_feed_forward": 0,
+    "codebook_weights": null,
     "cross_attention_hidden_size": null,
     "cross_attention_implementation_strategy": null,
     "decoder_start_token_id": null,
@@ -116,7 +119,7 @@
     "layerdrop": 0.0,
     "length_penalty": 1.0,
     "max_length": 20,
-    "max_position_embeddings": 4096,
+    "max_position_embeddings": 4311,
     "min_length": 0,
     "model_type": "parler_tts_decoder",
     "no_repeat_ngram_size": 0,
@@ -157,6 +160,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
+    "use_fused_lm_heads": false,
     "vocab_size": 1088
   },
   "decoder_start_token_id": 1025,
@@ -165,6 +169,7 @@
   "pad_token_id": 1024,
   "prompt_cross_attention": false,
   "text_encoder": {
+    "_attn_implementation_autoset": false,
     "_name_or_path": "google/flan-t5-large",
     "add_cross_attention": false,
     "architectures": [
@@ -249,6 +254,6 @@
     "vocab_size": 32128
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.40.2",
+  "transformers_version": "4.46.1",
   "vocab_size": 32128
 }

generation_config.json

@@ -2,11 +2,11 @@
   "_from_model_config": true,
   "bos_token_id": 1025,
   "decoder_start_token_id": 1025,
-  "min_new_tokens": 10,
   "do_sample": true,
   "eos_token_id": 1024,
   "guidance_scale": 1,
-  "max_length": 2580,
+  "max_length": 4150,
+  "min_new_tokens": 10,
   "pad_token_id": 1024,
-  "transformers_version": "4.40.2"
+  "transformers_version": "4.46.1"
 }

handler.py

@@ -1,44 +0,0 @@
-from typing import Dict, List, Any
-from parler_tts import ParlerTTSForConditionalGeneration
-from transformers import AutoTokenizer
-import torch
-
-class EndpointHandler:
-    def __init__(self, path=""):
-        # load model and processor from path
-        self.tokenizer = AutoTokenizer.from_pretrained(path)
-        self.model = ParlerTTSForConditionalGeneration.from_pretrained(path, torch_dtype=torch.float16).to("cuda")
-
-    def __call__(self, data: Dict[str, Any]) -> Dict[str, str]:
-        """
-        Args:
-            data (:dict:):
-                The payload with the text prompt and generation parameters.
-        """
-        # process input
-        inputs = data.pop("inputs", data)
-        voice_description = data.pop("voice_description", "data")
-        parameters = data.pop("parameters", None)
-
-        gen_kwargs = {"min_new_tokens": 10}
-        if parameters is not None:
-            gen_kwargs.update(parameters)
-
-        # preprocess
-        inputs = self.tokenizer(
-            text=[inputs],
-            padding=True,
-            return_tensors="pt",).to("cuda")
-        voice_description = self.tokenizer(
-            text=[voice_description],
-            padding=True,
-            return_tensors="pt",).to("cuda")
-
-        # pass inputs with all kwargs in data
-        with torch.autocast("cuda"):
-            outputs = self.model.generate(**voice_description, prompt_input_ids=inputs.input_ids, **gen_kwargs)
-
-        # postprocess the prediction
-        prediction = outputs[0].cpu().numpy().tolist()
-
-        return [{"generated_audio": prediction}]

preprocessor_config.json

@@ -1,10 +0,0 @@
-{
-  "chunk_length_s": null,
-  "feature_extractor_type": "EncodecFeatureExtractor",
-  "feature_size": 1,
-  "overlap": null,
-  "padding_side": "right",
-  "padding_value": 0.0,
-  "return_attention_mask": true,
-  "sampling_rate": 44100
-}

requirements.txt

@@ -1 +0,0 @@
-git+https://github.com/huggingface/parler-tts.git

tokenizer_config.json

@@ -927,7 +927,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_ids": 100,
   "model_max_length": 512,