1
pip install requests

1
import requests

1
SARVAM_API_KEY = "YOUR_SARVAM_API_KEY"

1
def read_file(file_path, lang_name):
2
    try:
3
        with open(file_path, "r", encoding="utf-8") as file:
4
            # Read the first 5 lines
5
            lines = [next(file) for _ in range(5)]
6
            print(f"=== {lang_name} Text (First Few Lines) ===")
7
            print("".join(lines))  # Print first few lines
8
9
            # Read the remaining content
10
            remaining_text = file.read()
11
12
            # Combine all text
13
            full_doc = "".join(lines) + remaining_text
14
15
            # Count total characters
16
            total_chars = len(full_doc)
17
            print(f"\nTotal number of characters in {lang_name} file:", total_chars)
18
19
            return full_doc
20
    except FileNotFoundError:
21
        print(f"Error: {file_path} not found.")
22
        return None
23
    except Exception as e:
24
        print(f"An error occurred while reading {file_path}: {e}")
25
        return None

1
# Read English and Hindi documents
2
english_doc = read_file("data/sample1.txt", "English")
3
hindi_doc = read_file("data/sample2.txt", "Hindi")

1
def chunk_text(text, max_length=1000):
2
    """Splits text into chunks of at most max_length characters while preserving word boundaries."""
3
    chunks = []
4
5
    while len(text) > max_length:
6
        split_index = text.rfind(" ", 0, max_length)  # Find the last space within limit
7
        if split_index == -1:
8
            split_index = max_length  # No space found, force split at max_length
9
10
        chunks.append(text[:split_index].strip())  # Trim spaces before adding
11
        text = text[split_index:].lstrip()  # Remove leading spaces for the next chunk
12
13
    if text:
14
        chunks.append(text.strip())  # Add the last chunk
15
16
    return chunks

1
# Split the text
2
english_text_chunks = chunk_text(english_doc)
3
4
# Display chunk info
5
print(f"Total Chunks: {len(english_text_chunks)}")
6
for i, chunk in enumerate(english_text_chunks[:3], 1):  # Show only first 3 chunks for preview
7
    print(f"\n=== Chunk {i} (Length: {len(chunk)}) ===\n{chunk}")

1
# Split the text
2
hindi_text_chunks = chunk_text(english_doc)
3
4
# Display chunk info
5
print(f"Total Chunks: {len(hindi_text_chunks)}")
6
for i, chunk in enumerate(hindi_text_chunks[:3], 1):  # Show only first 3 chunks for preview
7
    print(f"\n=== Chunk {i} (Length: {len(chunk)}) ===\n{chunk}")

1
import requests
2
3
# Define API request details
4
url = "https://api.sarvam.ai/transliterate"
5
headers = {
6
    "api-subscription-key": SARVAM_API_KEY,
7
    "Content-Type": "application/json"
8
}

1
# Send requests for each chunk
2
translated_texts = []
3
for idx, chunk in enumerate(hindi_text_chunks):
4
    payload = {
5
        "input": chunk,
6
        "source_language_code": "hi-IN",
7
        "target_language_code": "hi-IN",
8
        "spoken_form": True,
9
        "numerals_format": "international"
10
    }
11
12
    response = requests.post(url, json=payload, headers=headers)
13
14
    if response.status_code == 200:
15
        translated_text = response.json().get("transliterated_text", "Translation not available")
16
        translated_texts.append(translated_text)
17
        print(f"\n=== Translated Chunk {idx + 1} ===\n{translated_text}\n")
18
    else:
19
        print(f"Error: {response.status_code}, {response.text}")
20
21
# Combine all translated chunks
22
final_translation = "\n".join(translated_texts)
23
print("\n=== Final Translated Text ===")
24
print(final_translation)

1
# Define the payload for Romanization (Hindi to Latin script)
2
payload = {
3
    "input": "मैं ऑफिस जा रहा हूँ",
4
    "source_language_code": "hi-IN",
5
    "target_language_code": "en-IN",
6
    "spoken_form": True
7
}
8
9
# Send the request
10
response = requests.post(url, json=payload, headers=headers)
11
12
# Extract the transliterated text
13
if response.status_code == 200:
14
    transliterated_text = response.json().get("transliterated_text", "Translation not available")
15
    print("Romanized Text:", transliterated_text)
16
else:
17
    print(f"Error: {response.status_code}, {response.text}")

1
payload = {
2
    "input": "main office ja raha hun",
3
    "source_language_code": "hi-IN",
4
    "target_language_code": "hi-IN",
5
    "spoken_form": True
6
}
7
8
# Send the request
9
response = requests.post(url, json=payload, headers=headers)
10
11
# Extract the transliterated text
12
if response.status_code == 200:
13
    transliterated_text = response.json().get("transliterated_text", "Translation not available")
14
    print("Romanized Text:", transliterated_text)
15
else:
16
    print(f"Error: {response.status_code}, {response.text}")

1
payload = {
2
    "input": "मुझे कल 9:30am को appointment है",
3
    "source_language_code": "hi-IN",
4
    "target_language_code": "hi-IN",
5
    "spoken_form": True,
6
}
7
8
# Send the request
9
response = requests.post(url, json=payload, headers=headers)
10
11
# Extract the transliterated text
12
if response.status_code == 200:
13
    transliterated_text = response.json().get("transliterated_text", "Translation not available")
14
    print("Romanized Text:", transliterated_text)
15
else:
16
    print(f"Error: {response.status_code}, {response.text}")

1
payload = {
2
    "input": "मुझे कल 9:30am को appointment है",
3
    "source_language_code": "hi-IN",
4
    "target_language_code": "hi-IN",
5
    "spoken_form": True,
6
    "numerals_format": "native"
7
}
8
9
# Send the request
10
response = requests.post(url, json=payload, headers=headers)
11
12
# Extract the transliterated text
13
if response.status_code == 200:
14
    transliterated_text = response.json().get("transliterated_text", "Translation not available")
15
    print("Romanized Text:", transliterated_text)
16
else:
17
    print(f"Error: {response.status_code}, {response.text}")

1
payload = {
2
    "input": "मुझे कल 9:30am को appointment है",
3
    "source_language_code": "hi-IN",
4
    "target_language_code": "hi-IN",
5
    "spoken_form": True,
6
    "spoken_form_numerals_language": "english"
7
}
8
9
# Send the request
10
response = requests.post(url, json=payload, headers=headers)
11
12
# Extract the transliterated text
13
if response.status_code == 200:
14
    transliterated_text = response.json().get("transliterated_text", "Translation not available")
15
    print("Romanized Text:", transliterated_text)
16
else:
17
    print(f"Error: {response.status_code}, {response.text}")