add files

README.md

@@ -0,0 +1,150 @@
+---
+language: en
+datasets:
+- librispeech_asr
+tags:
+- audio
+- automatic-speech-recognition
+license: MIT
+---
+
+
+# S2T-MEDIUM-LIBRISPEECH-ASR
+
+`s2t-medium-librispeech-asr` is a Speech to Text Transformer (S2T) model trained for automatic speech recognition (ASR).
+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 an end-to-end sequence-to-sequence transformer model. It is trained with standard
+autoregressive cross-entropy loss and generates the transcripts autoregressively.
+
+## Intended uses & limitations
+
+This model can be used for end-to-end speech recognition (ASR).
+See the [model hub](https://huggingface.co/models?filter=speech_to_text_transformer) 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.*
+
+To install `torchaudio` run `pip install torchaudio`
+
+
+```python
+import torch
+from transformers import Speech2TextProcessor, Speech2TextTransformerForConditionalGeneration
+from datasets import load_dataset
+import soundfile as sf
+
+model = Speech2TextTransformerForConditionalGeneration.from_pretrained("facebook/s2t-medium-librispeech-asr")
+processor = Speech2Textprocessor.from_pretrained("facebook/s2t-medium-librispeech-asr")
+
+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)
+
+input_features = processor(
+    ds["speech"][0],
+    sampling_rate=16_000,
+    return_tensors="pt"
+).input_features  # Batch size 1
+generated_ids = model.generate(input_ids=input_features)
+
+transcription = processor.batch_decode(generated_ids)
+```
+
+#### Evaluation on LibriSpeech Test
+
+The following script shows how to evaluate this model on the [LibriSpeech](https://huggingface.co/datasets/librispeech_asr)
+*"clean"* and *"other"* test dataset.
+
+```python
+from datasets import load_dataset, load_metric
+from transformers import Speech2TextTransformerForConditionalGeneration, Speech2TextProcessor
+import soundfile as sf
+
+librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")  # change to "other" for other test dataset
+wer = load_metric("wer")
+
+model = Speech2TextTransformerForConditionalGeneration.from_pretrained("facebook/s2t-medium-librispeech-asr").to("cuda")
+processor = Speech2TextProcessor.from_pretrained("facebook/s2t-medium-librispeech-asr", do_upper_case=True)
+
+def map_to_array(batch):
+    speech, _ = sf.read(batch["file"])
+    batch["speech"] = speech
+    return batch
+
+librispeech_eval = librispeech_eval.map(map_to_array)
+
+def map_to_pred(batch):
+    features = processor(batch["speech"], sampling_rate=16000, padding=True, return_tensors="pt")
+    input_features = features.input_features.to("cuda")
+    attention_mask = features.attention_mask.to("cuda")
+
+    gen_tokens = model.generate(input_ids=input_features, attention_mask=attention_mask)
+    batch["transcription"] = processor.batch_decode(gen_tokens, skip_special_tokens=True)
+    return batch
+
+result = librispeech_eval.map(map_to_pred, batched=True, batch_size=8, remove_columns=["speech"])
+
+print("WER:", wer(predictions=result["transcription"], references=result["text"]))
+```
+
+*Result (WER)*:
+
+| "clean" | "other" |
+|:-------:|:-------:|
+| 3.5     | 7.8     |
+
+
+
+## Training data
+
+The S2T-MEDIUM-LIBRISPEECH-ASR is trained on [LibriSpeech ASR Corpus](https://www.openslr.org/12), a dataset consisting of
+approximately 1000 hours of 16kHz read English speech.
+
+
+## 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 10,000.
+
+
+### 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.
+
+
+### 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 +1,45 @@
+{
+  "activation_dropout": 0.15,
+  "activation_function": "relu",
+  "architectures": [
+    "Speech2TextTransformerForConditionalGeneration"
+  ],
+  "attention_dropout": 0.15,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "conv_channels": 1024,
+  "conv_kernel_sizes": [
+    5,
+    5
+  ],
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.15,
+  "early_stopping": true,
+  "encoder_attention_heads": 8,
+  "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_transformer",
+  "num_beams": 5,
+  "num_conv_layers": 2,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "transformers_version": "4.4.0.dev0",
+  "use_cache": true,
+  "vocab_size": 10000
+}

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "do_normalize": true,
+  "feature_size": 80,
+  "norm_means": true,
+  "norm_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 sha256:8b016d9dde06a7d3f73855d19ef597b61055a5ef6d9ec0d12132c7f4077e2aea
+size 284968270

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052a168787a9160b4b2ba54e4995e9600298812c34191ca3f70cea51cd4f5c1e
+size 416684

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": true, "tgt_lang": null, "lang_codes": null, "special_tokens_map_file": "/home/suraj/.cache/huggingface/transformers/f39f1499e9c4d2b3e803e3cad8a31c4cf3e626e1c69197d4cd6921e5c07007f9.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "tokenizer_file": null, "name_or_path": "hf_models_fb/s2t-small-librispeech-asr/"}