update weights

.ipynb_checkpoints/config-checkpoint.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
+}

README.md

@@ -0,0 +1,54 @@
+---
+language: en
+datasets:
+- librispeech_asr
+tags:
+- audio
+- automatic-speech-recognition
+license: apache-2.0
+---
+
+TODO: [To be filled]
+
+
+## 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
+from transformers import Speech2TextTransformerForConditionalGeneration, Speech2TextTransformerTokenizer
+import soundfile as sf
+from jiwer import wer
+
+librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")  # change to "other" for other test dataset
+
+model = Speech2TextTransformerForConditionalGeneration.from_pretrained("valhalla/s2t_librispeech_medium").to("cuda")
+tokenizer = Speech2TextTransformerTokenizer.from_pretrained("valhalla/s2t_librispeech_medium", 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 = tokenizer(batch["speech"], sample_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"] = tokenizer.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(result["text"], result["transcription"]))
+```
+
+*Result (WER)*:
+
+| "clean" | "other" |
+|---|---|
+| 3.5 | 7.8 |