Duplicate from awkyu/audiogen-medium

Co-authored-by: Alexander Kyu <awkyu@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,49 @@
+---
+license: cc-by-nc-4.0
+---
+
+# AudioGen - Medium - 1.5B
+
+AudioGen is an autoregressive transformer LM that synthesizes general audio conditioned on text (Text-to-Audio). 
+Internally, AudioGen operates over discrete representations learnt from the raw waveform, using an EnCodec tokenizer.
+
+AudioGen was presented at [AudioGen: Textually Guided Audio Generation](https://arxiv.org/abs/2209.15352) by *Felix Kreuk, Gabriel Synnaeve, Adam Polyak, Uriel Singer, Alexandre Défossez, Jade Copet, Devi Parikh, Yaniv Taigman, Yossi Adi*.
+
+AudioGen 1.5B is a variant of the original AudioGen model that follows [MusicGen](https://arxiv.org/abs/2306.05284) architecture. 
+More specifically, it is trained over a 16kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz with a delay pattern between the codebooks. 
+Having only 50 auto-regressive steps per second of audio, this AudioGen model allows faster generation while reaching similar performances to the original AudioGen model introduced in the paper.
+
+## Audiocraft Usage
+
+You can run AudioGen locally through the original [Audiocraft library]((https://github.com/facebookresearch/audiocraft):
+
+1. First install the [`audiocraft` library](https://github.com/facebookresearch/audiocraft)
+```
+pip install git+https://github.com/facebookresearch/audiocraft.git
+```
+
+2. Make sure to have [`ffmpeg`](https://ffmpeg.org/download.html) installed:
+```
+apt get install ffmpeg
+```
+
+3. Run the following Python code:
+
+```py
+import torchaudio
+from audiocraft.models import AudioGen
+from audiocraft.data.audio import audio_write
+
+model = AudioGen.get_pretrained('facebook/audiogen-medium')
+model.set_generation_params(duration=5)  # generate 5 seconds.
+descriptions = ['dog barking', 'sirenes of an emergency vehicule', 'footsteps in a corridor']
+wav = model.generate(descriptions)  # generates 3 samples.
+
+for idx, one_wav in enumerate(wav):
+    # Will save under {idx}.wav, with loudness normalization at -14 db LUFS.
+    audio_write(f'{idx}', one_wav.cpu(), model.sample_rate, strategy="loudness", loudness_compressor=True)
+```
+
+## Model details
+
+See [AudioGen's model card](https://github.com/facebookresearch/audiocraft/blob/main/model_cards/AUDIOGEN_MODEL_CARD.md).

compression_state_dict.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a520e64ca99226a9956f83b06df0617b713183fcdc384779883a6bb46dc1095
+size 235740815

config.json

@@ -0,0 +1,298 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "MusicgenForConditionalGeneration"
+  ],
+  "audio_encoder": {
+    "_name_or_path": "facebook/encodec_32khz",
+    "add_cross_attention": false,
+    "architectures": [
+      "EncodecModel"
+    ],
+    "audio_channels": 1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_length_s": null,
+    "chunk_size_feed_forward": 0,
+    "codebook_dim": 128,
+    "codebook_size": 2048,
+    "compress": 2,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dilation_growth_rate": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 128,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "kernel_size": 7,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "last_kernel_size": 7,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "encodec",
+    "no_repeat_ngram_size": 0,
+    "norm_type": "weight_norm",
+    "normalize": false,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_filters": 64,
+    "num_lstm_layers": 2,
+    "num_residual_layers": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "overlap": null,
+    "pad_mode": "reflect",
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "residual_kernel_size": 3,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sampling_rate": 32000,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "target_bandwidths": [
+      2.2
+    ],
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "transformers_version": "4.31.0.dev0",
+    "trim_right_ratio": 1.0,
+    "typical_p": 1.0,
+    "upsampling_ratios": [
+      8,
+      5,
+      4,
+      4
+    ],
+    "use_bfloat16": false,
+    "use_causal_conv": false,
+    "use_conv_shortcut": false
+  },
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 2048,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 4096,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 2048,
+    "min_length": 0,
+    "model_type": "musicgen_decoder",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 4,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 2048,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.31.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 2048
+  },
+  "is_encoder_decoder": true,
+  "model_type": "musicgen",
+  "text_encoder": {
+    "_name_or_path": "t5-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "T5ForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "d_ff": 3072,
+    "d_kv": 64,
+    "d_model": 768,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "relu",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1,
+    "exponential_decay_length_penalty": null,
+    "feed_forward_proj": "relu",
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "is_gated_act": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "t5",
+    "n_positions": 512,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_decoder_layers": 12,
+    "num_heads": 12,
+    "num_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "summarization": {
+        "early_stopping": true,
+        "length_penalty": 2.0,
+        "max_length": 200,
+        "min_length": 30,
+        "no_repeat_ngram_size": 3,
+        "num_beams": 4,
+        "prefix": "summarize: "
+      },
+      "translation_en_to_de": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to German: "
+      },
+      "translation_en_to_fr": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to French: "
+      },
+      "translation_en_to_ro": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to Romanian: "
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.31.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32128
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null
+}

handler.py

@@ -0,0 +1,38 @@
+from typing import Dict, List, Any
+from transformers import AutoProcessor, MusicgenForConditionalGeneration
+import torch
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        # load model and processor from path
+        self.processor = AutoProcessor.from_pretrained(path)
+        self.model = MusicgenForConditionalGeneration.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)
+        parameters = data.pop("parameters", None)
+
+        # preprocess
+        inputs = self.processor(
+            text=[inputs],
+            padding=True,
+            return_tensors="pt",).to("cuda")
+
+        # pass inputs with all kwargs in data
+        if parameters is not None:
+            with torch.autocast("cuda"):
+                outputs = self.model.generate(**inputs, **parameters)
+        else:
+            with torch.autocast("cuda"):
+                outputs = self.model.generate(**inputs,)
+
+        # postprocess the prediction
+        prediction = outputs[0].cpu().numpy().tolist()
+
+        return [{"generated_audio": prediction}]

requirements.txt

@@ -0,0 +1,2 @@
+transformers==4.31.0
+accelerate>=0.20.3

state_dict.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b20997834de1ca47d6a31d00a5dc37019b279c7c8f250fd482d56def04faaa
+size 3678455287