add files

README.md

@@ -0,0 +1,122 @@
+---
+language:
+- en
+- de
+datasets:
+- mustc
+tags:
+- audio
+- speech-translation
+- automatic-speech-recognition
+license: MIT
+---
+
+
+# S2T-SMALL-MUSTC-EN-DE-ST
+
+`s2t-small-mustc-en-de-st` is a Speech to Text Transformer (S2T) model trained for end-to-end Speech Translation (ST).
+The S2T model was proposed in [this paper](https://arxiv.org/abs/2010.05171) and released in
+[this repository](https://github.com/pytorch/fairseq/tree/master/examples/speech_to_text)
+
+
+## Model description
+
+S2T is a transformer-based seq2seq (encoder-decoder) model designed for end-to-end Automatic Speech Recognition (ASR) and Speech
+Translation (ST). It uses a convolutional downsampler to reduce the length of speech inputs by 3/4th before they are
+fed into the encoder. The model is trained with standard autoregressive cross-entropy loss and generates the
+transcripts/translations autoregressively.
+
+## Intended uses & limitations
+
+This model can be used for end-to-end English speech to German text translation.
+See the [model hub](https://huggingface.co/models?filter=speech_to_text) to look for other S2T checkpoints.
+
+
+### How to use
+
+As this a standard sequence to sequence transformer model, you can use the `generate` method to generate the
+transcripts by passing the speech features to the model.
+
+*Note: The `Speech2TextProcessor` object uses [torchaudio](https://github.com/pytorch/audio)  to extract the
+filter bank features. Make sure to install the `torchaudio` package before running this example.*
+
+You could either install those as extra speech dependancies with
+`pip install transformers"[speech, sentencepiece]"` or install the packages seperatly 
+with `pip install torchaudio sentencepiece`.
+
+
+```python
+import torch
+from transformers import Speech2TextProcessor, Speech2TextForConditionalGeneration
+from datasets import load_dataset
+import soundfile as sf
+
+model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-mustc-en-de-st")
+processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-mustc-en-de-st")
+
+def map_to_array(batch):
+    speech, _ = sf.read(batch["file"])
+    batch["speech"] = speech
+    return batch
+
+ds = load_dataset(
+    "patrickvonplaten/librispeech_asr_dummy",
+    "clean",
+    split="validation"
+)
+ds = ds.map(map_to_array)
+
+inputs = processor(
+    ds["speech"][0],
+    sampling_rate=16_000,
+    return_tensors="pt"
+)
+generated_ids = model.generate(input_ids=inputs["input_features"], attention_mask=inputs["attention_mask"])
+
+translation = processor.batch_decode(generated_ids, skip_special_tokens=True)
+```
+
+
+## Training data
+
+The s2t-small-mustc-en-de-st is trained on English-German subset of [MuST-C](https://ict.fbk.eu/must-c/).
+MuST-C is a multilingual speech translation corpus whose size and quality facilitates the training of end-to-end systems
+for speech translation from English into several languages. For each target language, MuST-C comprises several hundred
+hours of audio recordings from English TED Talks, which are automatically aligned at the sentence level with their manual
+transcriptions and translations.
+
+
+## Training procedure
+
+### Preprocessing
+
+The speech data is pre-processed by extracting Kaldi-compliant 80-channel log mel-filter bank features automatically from
+WAV/FLAC audio files via PyKaldi or torchaudio. Further utterance-level CMVN (cepstral mean and variance normalization)
+is applied to each example.
+
+The texts are lowercased and tokenized using SentencePiece and a vocabulary size of 8,000.
+
+
+### Training
+
+The model is trained with standard autoregressive cross-entropy loss and using [SpecAugment](https://arxiv.org/abs/1904.08779).
+The encoder receives speech features, and the decoder generates the transcripts autoregressively. To accelerate
+model training and for better performance the encoder is pre-trained for English ASR.
+
+## Evaluation results
+
+MuST-C test results for en-de (BLEU score): 22.7
+
+
+
+### BibTeX entry and citation info
+
+```bibtex
+@inproceedings{wang2020fairseqs2t,
+  title = {fairseq S2T: Fast Speech-to-Text Modeling with fairseq},
+  author = {Changhan Wang and Yun Tang and Xutai Ma and Anne Wu and Dmytro Okhonko and Juan Pino},
+  booktitle = {Proceedings of the 2020 Conference of the Asian Chapter of the Association for Computational Linguistics (AACL): System Demonstrations},
+  year = {2020},
+}
+
+```

config.json

@@ -0,0 +1,46 @@
+{
+  "activation_dropout": 0.1,
+  "activation_function": "relu",
+  "architectures": [
+    "Speech2TextForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "conv_channels": 1024,
+  "conv_kernel_sizes": [
+    5,
+    5
+  ],
+  "d_model": 256,
+  "decoder_attention_heads": 4,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 4,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "input_channels": 1,
+  "input_feat_per_channel": 80,
+  "is_encoder_decoder": true,
+  "max_length": 200,
+  "max_source_positions": 6000,
+  "max_target_positions": 1024,
+  "model_type": "speech_to_text",
+  "num_beams": 5,
+  "num_conv_layers": 2,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.4.0.dev0",
+  "use_cache": true,
+  "vocab_size": 8000
+}

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "do_ceptral_normalize": true,
+  "feature_size": 80,
+  "normalize_means": true,
+  "normalize_vars": true,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a189f656f350aedd417daf56bcc43b7d481cd2a056f808ef3318a6b38eaedb98
+size 124411397

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e4fa624a9669edfb705c3f69b515d8fecf847e0f93e70f8d1f8ab024ce7939
+size 380089

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "do_upper_case": false, "do_lower_case": false, "tgt_lang": null, "lang_codes": null}