transformers: Logits size does not match vocabulary size when using pyctcdecode for a fine-tuned wav2vec 2.0 model

Environment info

• transformers version: 4.17.0.dev0
• Platform: Linux-5.4.0-1063-azure-x86_64-with-glibc2.29
• Python version: 3.8.10
• PyTorch version (GPU?): 1.10.2+cu102 (True)
• Tensorflow version (GPU?): 2.6.0 (True)
• Flax version (CPU?/GPU?/TPU?): not installed (NA)
• Jax version: not installed
• JaxLib version: not installed
• Using GPU in script?: Yes (device = ‘cuda’)
• Using distributed or parallel set-up in script?: No

Who can help

@patrickvonplaten, @anton-l

Dataset used

https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0

Information

Model I am using: https://huggingface.co/Iskaj/xlsr300m_cv_7.0_nl_lm, (dataset = https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0) The model fine-tuned version of https://huggingface.co/facebook/wav2vec2-xls-r-300m

The problem arises when using:

import torch
from datasets import load_dataset
from transformers import AutoModelForCTC, AutoProcessor
import torchaudio.functional as F

model_id = "Iskaj/xlsr300m_cv_7.0_nl_lm"

sample_iter = iter(load_dataset("mozilla-foundation/common_voice_8_0", "nl", split="test", streaming=True, use_auth_token=True))

sample = next(sample_iter)
resampled_audio = F.resample(torch.tensor(sample["audio"]["array"]), 48_000, 16_000).numpy()

model = AutoModelForCTC.from_pretrained(model_id)
processor = AutoProcessor.from_pretrained(model_id)

input_values = processor(resampled_audio, return_tensors="pt").input_values

with torch.no_grad():
    logits = model(input_values).logits

transcription = processor.batch_decode(logits.numpy()).text

To reproduce

Steps to reproduce the behavior:

1. install packages using: !pip install https://github.com/kpu/kenlm/archive/master.zip pyctcdecode !pip install git+https://github.com/huggingface/transformers.git !pip install git+https://github.com/huggingface/datasets.git !pip install torchaudio soundfile librosa Levenshtein telwoord wandb jiwer
2. run:

import torch
from datasets import load_dataset
from transformers import AutoModelForCTC, AutoProcessor
import torchaudio.functional as F

model_id = "Iskaj/xlsr300m_cv_7.0_nl_lm"

sample_iter = iter(load_dataset("mozilla-foundation/common_voice_8_0", "nl", split="test", streaming=True, use_auth_token=True))

sample = next(sample_iter)
resampled_audio = F.resample(torch.tensor(sample["audio"]["array"]), 48_000, 16_000).numpy()

model = AutoModelForCTC.from_pretrained(model_id)
processor = AutoProcessor.from_pretrained(model_id)

input_values = processor(resampled_audio, return_tensors="pt").input_values

with torch.no_grad():
    logits = model(input_values).logits

transcription = processor.batch_decode(logits.numpy()).text

1. Observe the error: `ValueError: Input logits of size 48, but vocabulary is size 50

Expected behavior

I would expect pyctc-decode to work correctly and give me a transcription. I suspect it has something to do with <s> and </s>. I’ve been struggling a bit with the length of the logits not matching up with the length of the vocabulary, when using pyctcdecode. For example in this repo that uses the LM: https://huggingface.co/patrickvonplaten/wav2vec2-base-100h-with-lm/blob/main/vocab.json the vocab.json includes and , but in this repo it doesn’t: https://huggingface.co/hf-test/xls-r-300m-sv/blob/main/vocab.json Maybe that helps