BUGFIX: update pipeline_cli to work with new pipeline refactor

[rahul-tuli]

This PR accomplishes the following:

• Update deepsparse.transformers.pipelines_cli to work with new pipelines refactor
• Update a few typos in docstring in pipeline.py
• Also noting that from deepsparse import Pipeline works

The local tests performed are as follows:

deepsparse.run_inference \
    --model-path zoo:nlp/token_classification/bert-base/pytorch/huggingface/conll2003/12layer_pruned80_quant-none-vnni \
    --task ner \
    --data input.txt

Input (input.txt):

My name is rahul and i am a student of computer science and engineering.

Output in out.json
```json
"{\"predictions\": [[{\"entity\": \"LABEL_0\", \"score\": 0.9998608231544495, \"index\": 1, \"word\": \"my\", \"start\": 0, \"end\": 2, \"is_grouped\": false}, {\"entity\": \"LABEL_0\", \"score\": 0.9996172785758972, \"index\": 2, \"word\": \"name\", \"start\": 3, \"end\": 7, \"is_grouped\": false}, {\"entity\": \"LABEL_0\", \"score\": 0.9998311996459961, \"index\": 3, \"word\": \"is\", \"start\": 8, \"end\": 10, \"is_grouped\": false}, {\"entity\": \"LABEL_1\", \"score\": 0.999155580997467, \"index\": 4, \"word\": \"ra\", \"start\": 11, \"end\": 13, \"is_grouped\": false}, {\"entity\": \"LABEL_1\", \"score\": 0.7973057627677917, \"index\": 5, \"word\": \"##hul\", \"start\": 13, \"end\": 16, \"is_grouped\": false}, {\"entity\": \"LABEL_0\", \"score\": 0.9999052286148071, \"index\": 6, \"word\": \"and\", \"start\": 17, \"end\": 20, \"is_grouped\": false}, {\"entity\": \"LABEL_0\", \"score\": 0.999871015548706, \"index\": 7, \"word\": \"i\", \"start\": 21, \"end\": 22, \"is_grouped\": false}, {\"entity\": \"LABEL_0\", \"score\": 0.9999074339866638, \"index\": 8, \"word\": \"am\", \"start\": 23, \"end\": 25, \"is_grouped\": false}, {\"entity\": \"LABEL_0\", \"score\": 0.9998987913131714, \"index\": 9, \"word\": \"a\", \"start\": 26, \"end\": 27, \"is_grouped\": false}, {\"entity\": \"LABEL_0\", \"score\": 0.9998655319213867, \"index\": 10, \"word\": \"student\", \"start\": 28, \"end\": 35, \"is_grouped\": false}, {\"entity\": \"LABEL_0\", \"score\": 0.9998788237571716, \"index\": 11, \"word\": \"of\", \"start\": 36, \"end\": 38, \"is_grouped\": false}, {\"entity\": \"LABEL_0\", \"score\": 0.9884167313575745, \"index\": 12, \"word\": \"computer\", \"start\": 39, \"end\": 47, \"is_grouped\": false}, {\"entity\": \"LABEL_0\", \"score\": 0.9930113554000854, \"index\": 13, \"word\": \"science\", \"start\": 48, \"end\": 55, \"is_grouped\": false}, {\"entity\": \"LABEL_0\", \"score\": 0.9991596937179565, \"index\": 14, \"word\": \"and\", \"start\": 56, \"end\": 59, \"is_grouped\": false}, {\"entity\": \"LABEL_0\", \"score\": 0.9913791418075562, \"index\": 15, \"word\": \"engineering\", \"start\": 60, \"end\": 71, \"is_grouped\": false}, {\"entity\": \"LABEL_0\", \"score\": 0.9998722672462463, \"index\": 16, \"word\": \".\", \"start\": 71, \"end\": 72, \"is_grouped\": false}]]}"

Tests to check pipeline import:

Python 3.8.12 (default, Jan 15 2022, 18:39:47) 
[GCC 7.5.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> from deepsparse import Pipeline
>>> Pipeline.create(
... task="ner"
... )
DeepSparse Engine, Copyright 2021-present / Neuralmagic, Inc. version: 0.12.0 (5f03c9f3) (release) (optimized) (system=avx512, binary=avx512)
<deepsparse.transformers.pipelines.token_classification.TokenClassificationPipeline object at 0x7f37b31bc6d0>
>>>