1
!pip install -Uqq sarvamai

1
from sarvamai import SarvamAI

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("sample1.txt", "English")
3
hindi_doc = read_file("sample2.txt", "Hindi")

1
def chunk_text(text, max_length=2000):
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(
7
    english_text_chunks[:3], 1
8
):  # Show only first 3 chunks for preview
9
    print(f"\n=== Chunk {i} (Length: {len(chunk)}) ===\n{chunk}")

1
# Split the text
2
hindi_text_chunks = chunk_text(hindi_doc)
3
4
# Display chunk info
5
print(f"Total Chunks: {len(hindi_text_chunks)}")
6
for i, chunk in enumerate(
7
    hindi_text_chunks[:3], 1
8
):  # Show only first 3 chunks for preview
9
    print(f"\n=== Chunk {i} (Length: {len(chunk)}) ===\n{chunk}")

1
# Sample Hindi text (can be up to 2000 characters per chunk for sarvam-translate:v1)
2
hindi_text = "भारत एक महान देश है। इसकी संस्कृति बहुत पुरानी और समृद्ध है।"
3
4
# Simple chunking for demonstration (no chunk exceeds 2000 characters)
5
hindi_text_chunks = [hindi_text]  # In real cases, you would split longer text here
6
7
# Loop through each chunk and translate
8
for idx, chunk in enumerate(hindi_text_chunks):
9
    response = client.text.translate(
10
        input=chunk,
11
        source_language_code="hi-IN",
12
        target_language_code="sa-IN",
13
        speaker_gender="Male",
14
        mode="formal",
15
        model="sarvam-translate:v1",
16
    )
17
18
    # Print the translated output
19
    print(f"Chunk {idx + 1} Translation:\n{response.translated_text}\n")

1
# Initialize SarvamAI
2
3
from sarvamai import SarvamAI
4
5
client = SarvamAI(api_subscription_key=SARVAM_API_KEY)

1
translated_texts = []
2
for idx, chunk in enumerate(english_text_chunks):
3
    response = client.text.translate(
4
        input=chunk,
5
        source_language_code="en-IN",
6
        target_language_code="sa-IN",
7
        speaker_gender="Male",
8
        mode="formal",
9
        model="sarvam-translate:v1",
10
        enable_preprocessing=False,
11
    )
12
13
    translated_text = response.translated_text
14
    print(f"\n=== Translated Chunk {idx + 1} ===\n{translated_text}\n")
15
    translated_texts.append(translated_text)
16
17
# Combine all translated chunks
18
final_translation = "\n".join(translated_texts)
19
print("\n=== Final Translated Text in Sanskrit ===")
20
print(final_translation)

1
translated_texts = []
2
for idx, chunk in enumerate(hindi_text_chunks):
3
    response = client.text.translate(
4
        input=chunk,
5
        source_language_code="hi-IN",
6
        target_language_code="sd-IN",
7
        speaker_gender="Male",
8
        mode="formal",
9
        model="sarvam-translate:v1",
10
        enable_preprocessing=False,
11
    )
12
13
    translated_text = response.translated_text
14
    print(f"\n=== Translated Chunk {idx + 1} ===\n{translated_text}\n")
15
    translated_texts.append(translated_text)
16
17
# Combine all translated chunks
18
final_translation = "\n".join(translated_texts)
19
print("\n=== Final Translated Text in Sindhi ===")
20
print(final_translation)

1
translated_texts = []
2
for idx, chunk in enumerate(hindi_text_chunks):
3
    response = client.text.translate(
4
        input=chunk,
5
        source_language_code="hi-IN",
6
        target_language_code="bn-IN",
7
        speaker_gender="Male",
8
        mode="formal",
9
        model="sarvam-translate:v1",
10
        enable_preprocessing=False,
11
    )
12
13
    translated_text = response.translated_text
14
    print(f"\n=== Translated Chunk {idx + 1} ===\n{translated_text}\n")
15
    translated_texts.append(translated_text)
16
17
# Combine all translated chunks
18
final_translation = "\n".join(translated_texts)
19
print("\n=== Translated Text Chunks in Bengali ===")
20
print(final_translation)

1
# To highlight the difference between the models lets use the below example.
2
full_text = (
3
    "The invoice total is $3,450.75, due by 15th March 2025. Contact us at support@example.com for queries. "
4
    "Order #987654321 was placed on 02/29/2024. Your tracking ID is TRK12345678."
5
)

1
response = client.text.translate(
2
    input=full_text,
3
    source_language_code="en-IN",
4
    target_language_code="hi-IN",
5
    speaker_gender="Male",
6
    mode="formal",
7
    model="sarvam-translate:v1",
8
    enable_preprocessing=False,
9
)
10
translated_text = response.translated_text
11
print("\n=== Translated Text ===\n", translated_text)

1
response = client.text.translate(
2
    input=full_text,
3
    source_language_code="en-IN",
4
    target_language_code="hi-IN",
5
    speaker_gender="Male",
6
    mode="classic-colloquial",
7
    model="mayura:v1",
8
    enable_preprocessing=False,
9
)
10
translated_text = response.translated_text
11
print("\n=== Translated Text ===\n", translated_text)

1
response = client.text.translate(
2
    input=full_text,
3
    source_language_code="en-IN",
4
    target_language_code="hi-IN",
5
    speaker_gender="Male",
6
    mode="modern-colloquial",
7
    model="mayura:v1",
8
    enable_preprocessing=False,
9
)
10
translated_text = response.translated_text
11
print("\n=== Translated Text ===\n", translated_text)

1
response = client.text.translate(
2
    input=full_text,
3
    source_language_code="en-IN",
4
    target_language_code="hi-IN",
5
    speaker_gender="Female",
6
    mode="formal",
7
    model="sarvam-translate:v1",
8
    enable_preprocessing=False,
9
)
10
translated_text = response.translated_text
11
print("\n=== Translated Text ===\n", translated_text)

1
response = client.text.translate(
2
    input=full_text,
3
    source_language_code="en-IN",
4
    target_language_code="hi-IN",
5
    speaker_gender="Male",
6
    mode="formal",
7
    model="sarvam-translate:v1",
8
    enable_preprocessing=False,
9
)
10
translated_text = response.translated_text
11
print("\n=== Translated Text ===\n", translated_text)

1
response = client.text.translate(
2
    input=full_text,
3
    source_language_code="en-IN",
4
    target_language_code="hi-IN",
5
    speaker_gender="Male",
6
    mode="formal",
7
    model="sarvam-translate:v1",
8
    enable_preprocessing=False,
9
    numerals_format="native",
10
)
11
translated_text = response.translated_text
12
print("\n=== Translated Text ===\n", translated_text)

1
response = client.text.translate(
2
    input=full_text,
3
    source_language_code="en-IN",
4
    target_language_code="hi-IN",
5
    speaker_gender="Male",
6
    mode="formal",
7
    model="sarvam-translate:v1",
8
    enable_preprocessing=False,
9
    numerals_format="international",
10
)
11
translated_text = response.translated_text
12
print("\n=== Translated Text ===\n", translated_text)

1
response = client.text.translate(
2
    input=full_text,
3
    source_language_code="en-IN",
4
    target_language_code="hi-IN",
5
    speaker_gender="Male",
6
    mode="modern-colloquial",
7
    model="mayura:v1",
8
    enable_preprocessing=False,
9
    output_script="roman",
10
    numerals_format="international",
11
)
12
translated_text = response.translated_text
13
print("\n=== Translated Text ===\n", translated_text)

1
response = client.text.translate(
2
    input=full_text,
3
    source_language_code="en-IN",
4
    target_language_code="hi-IN",
5
    speaker_gender="Male",
6
    mode="modern-colloquial",
7
    model="mayura:v1",
8
    enable_preprocessing=False,
9
    output_script="spoken-form-in-native",
10
    numerals_format="international",
11
)
12
translated_text = response.translated_text
13
print("\n=== Translated Text ===\n", translated_text)

1
response = client.text.translate(
2
    input=full_text,
3
    source_language_code="en-IN",
4
    target_language_code="hi-IN",
5
    speaker_gender="Male",
6
    mode="modern-colloquial",
7
    model="mayura:v1",
8
    enable_preprocessing=False,
9
    output_script="fully-native",
10
    numerals_format="international",
11
)
12
translated_text = response.translated_text
13
print("\n=== Translated Text ===\n", translated_text)